I am a visual computing researcher—computer vision, computer graphics, and human-computer interaction. My lab develops techniques for image and video creation, editing, analysis, and interaction. This requires image and scene reconstruction techniques, especially from multi-camera systems and for complex dynamic scenes, and with applications on 2D, multi-view, and VR/AR displays.



Practical Scene & Object Reconstruction
How do we push neural reconstruction towards production quality at the scales and fidelities real graphics applications need—large scenes, unstructured camera arrays, physically-faithful shading?
2020–now

Practical Scene & Object Reconstruction

How do we push neural reconstruction towards production quality at the scales and fidelities real graphics applications need—large scenes, unstructured camera arrays, physically-faithful shading?

Neural scene representations (NeRFs, Gaussian splats) capture high visual fidelity, but typically work on small bounded scenes captured under controlled conditions. To bring the same machinery to production graphics, we work through the practical bottlenecks: scaling to large indoor and outdoor scenes, handling unstructured (non-rig) capture, integrating physically-correct light transport, and stabilising the optimisation when geometry is otherwise ambiguous.

My long collaboration with Weiwei Xu and Hujun Bao at Zhejiang has tackled one bottleneck per year—distributed tile-MLPs for large indoor scenes (SNISR, SIGGRAPH 2022), bundle-adjusting NeRFs with ADMM consensus over tiles at large scale (ScaNeRF, SIGGRAPH Asia 2023), local Gaussian density mixtures for unstructured capture with curved-surface reflections (LGDM, SIGGRAPH Asia 2024), and differentiable area-light shading for material recovery (EOR, SIGGRAPH Asia 2025). Shape from Tracing (3DV 2020) sits at the head of the line: our early step that used differentiable path tracing—full global illumination, not just shading—as the forward model for joint geometry and SVBRDF recovery.

Authors

Hujun Bao · Bach-Thuan Bui · Dongyoung Choi · Jaemin Cho · Loudon Cohen · Zheng Dong · Michael Fairley · Yaoan Gao · Purvi Goel · James Guesman · Hyunho Ha · Qixing Huang · Hyeonjoong Jang · Woohyun Kang · Hakyeong Kim · Min H. Kim · Andreas Meuleman · Minh-Hieu Nguyen · Yifan Peng · Daniel Ritchie · Belal Shaheen · Yujun Shen · Shubham · Vikas Thamizharasan · Chi Wang · Huamin Wang · Qi Wang · Michael Wu · Tim Wu · Xiuchao Wu · Jiamin Xu · Weiwei Xu · Matthew David Zane · Xin Zhang · Zihan Zhu · Changqing Zou

Papers in this thread

Shape from Tracing: Towards Reconstructing 3D Object Geometry and SVBRDF Material from Images via Differentiable Path Tracing
International Conference on 3D Vision (3DV), 2020
Uses differentiable path tracing—with global illumination effects like interreflection in the forward model—to refine a coarse mesh and its per-facet SVBRDF, so shading, shadow, and material are jointly disambiguated from images captured by phone and consumer 360 camera.
Scalable Neural Indoor Scene Rendering
Transactions on Graphics (SIGGRAPH), 2022
Tiles a large indoor scene and assigns a small MLP per tile, with a separate view-dependent branch for reflections, so training distributes across GPUs and rendering stays interactive—on scenes over 100 square metres.
ScaNeRF: Scalable Bundle-Adjusting Neural Radiance Fields for Large-Scale Scene Rendering
Transactions on Graphics (SIGGRAPH Asia), 2023
Pushes the tiled-NeRF idea into the bundle-adjusting regime: each tile carries a hash grid plus diffuse and specular MLPs, and ADMM reaches camera-pose consensus across tiles, with a specular-aware warping loss giving the poses a second optimisation path.
Local Gaussian Density Mixtures for Unstructured Lumigraph Rendering
SIGGRAPH Asia Conference Papers, 2024
Targets curved-surface reflections and refractions—exactly where view-consistent global density models break—with a per-view Gaussian-mixture density along each ray, then warps and fuses these local volumes with learned blending weights for unstructured lumigraph rendering.
Efficient Object Reconstruction with Differentiable Area Light Shading
SIGGRAPH Asia Conference Papers, 2025
Replaces point lights with active area lighting during capture, then differentiates through linearly transformed cosines plus shadow visibility weighting for shading—recovering material at +3 dB relighting PSNR or matching point-light quality from a fifth of the photos.

Related papers

OmniSDF: Scene Reconstruction using Omnidirectional Signed Distance Functions and Adaptive Binoctrees
Computer Vision and Pattern Recognition (CVPR), 2024
Reconstructs scenes captured by a small-baseline circular sweep of a 360 camera by placing an SDF inside an adaptively subdivided spherical binoctree, whose geometry matches the capture setting and keeps memory in line with detail.
Splat-based Gradient-domain Fusion for Seamless View Transition
International Conference on 3D Vision (3DV), 2026
Tackles the sparse-view, wide-baseline regime where Gaussian splatting drops geometry—anchors it with two-view stereo, fills intermediate viewpoints via reprojection, and fuses in the gradient domain so colour transitions stay smooth across views.
TreeDGS: Aerial Gaussian Splatting for Distant DBH Measurement
MDPI Remote Sensing, 2026
Treats aerial Gaussian splatting as a measurement instrument: trunks span only a few pixels from altitude, so the method extracts a dense opacity-weighted point set, isolates trunk samples, and fits solid circles to estimate diameter-at-breast-height—4.79 cm RMSE, below a LiDAR baseline.
Monocular Dynamic 3D Reconstruction
When the input is only ordinary RGB video—no depth sensor, no rig—can we recover dynamic 3D scene geometry well enough to compete with depth-sensor-supervised methods?
2023–now

Monocular Dynamic 3D Reconstruction

When the input is only ordinary RGB video—no depth sensor, no rig—can we recover dynamic 3D scene geometry well enough to compete with depth-sensor-supervised methods?

Monocular dynamic 3D reconstruction takes a single moving camera observing a deforming scene and tries to recover a complete 4D representation—geometry, appearance, motion—over the captured time window. The problem is fundamentally under-constrained at any one instant, and progress depends on how well the chosen scene representation and supervision signals work together.

Yiqing Liang's PhD drove this arc of our work. Starting from semantic attention flow fields built atop a dynamic NeRF at ICCV 2023, we moved to a forward-warping Gaussian deformation formulation (GauFRe, with Meta colleagues) for real-time rendering, then to a TMLR benchmark (MonoDyGauBench) that puts the recent flood of monocular dynamic Gaussian methods on a like-for-like footing. Our latest paper (Zero-MSF, with NVIDIA) abandons per-scene optimisation entirely and trains a feed-forward predictor for scene flow that generalises zero-shot to in-the-wild video.

Authors

Abhishek Badki · Orazio Gallo · Leonidas J. Guibas · Adam Harley · Numair Khan · Eliot Laidlaw · Douglas Lanman · Yiqing Liang · Runfeng Li · Zhengqin Li · Alexander Meyerowitz · Thu Nguyen-Phuoc · Mikhail Okunev · Srinath Sridhar · Hang Su · Mikaela Angelina Uy · Lei Xiao

Papers in this thread

Semantic Attention Flow Fields for Monocular Dynamic Scene Decomposition
International Conference on Computer Vision (ICCV), 2023
Reconstructs a 4D neural volume carrying not just colour and density but also scene flow, semantics, and attention, then uses the latter two to decompose foreground objects from background across spacetime without supervision.
GauFRe🧇: Gaussian Deformation Fields for Real-time Dynamic Novel View Synthesis
arXiv (Dec. 2023) + WACV, 2025
Casts monocular dynamic reconstruction as a canonical Gaussian template plus a forward-warping deformation field, with a separate static component initialised to absorb non-moving regions so the deformation focuses on what actually moves. Trains in roughly twenty minutes and renders in real time.
Monocular Dynamic Gaussian Splatting: Fast, Brittle, and Scene Complexity Rules
Transactions on Machine Learning Research (TMLR), 2025
An apples-to-apples benchmark of monocular dynamic Gaussian splatting methods, categorised by motion representation. Method differences are resolvable on synthetic data but get swamped by real-world scene complexity, and the optimisation is uniformly brittle.
Zero-Shot Monocular Scene Flow Estimation in the Wild
Computer Vision and Pattern Recognition (CVPR), 2025
A feed-forward model that jointly predicts geometry and scene flow, trained on a one-million-sample synthetic recipe. Generalises zero-shot to casual DAVIS video and RoboTAP manipulation scenes—no per-scene optimisation required.
Active Illumination for Dynamic 3D Reconstruction
Can physically modelling active illumination directly from raw sensor measurements improve scene estimation and avoid errors from derived depth?
2021–now

Active Illumination for Dynamic 3D Reconstruction

Can physically modelling active illumination directly from raw sensor measurements improve scene estimation and avoid errors from derived depth?

Time-of-flight and structured-light cameras are typically used as depth sensors: their raw measurements are processed into a per-pixel depth map, and downstream reconstruction methods treat that depth as input. But depth processing makes simplifying assumptions about the scene, creating noise in low-reflectance regions, flying pixels under multi-path interference, and motion artifacts in fast-moving scenes—each depth estimate needs multiple illumination readings. Further, derived depth is difficult to integrate with other sensor modalities, like colour cameras.

Thread overview diagram

Our work rethinks reconstruction for heterogeneous multi-shot imaging processes. Built upon a differentiable forward model of how the active illumination produces the raw sensor output for a given scene, our methods optimise a 4D volumetric scene representation (like NeRF or 3DGS) so that rendered measurements match what the sensor captured. This lets us integrate sensor measurements over spacetime in a principled way, including across modalities, to reduce noise, resolve ambiguities in multi-shot sensing, and improve robustness to multi-path interference. And since we model motion over time, we can resample fast motion—a swinging baseball bat—into slow motion.

Authors

Benjamin Attal · Anh Duong · Aaron Gokaslan · Zixuan Guo · Changil Kim · Hakyeong Kim · Min H. Kim · Eliot Laidlaw · Runfeng Li · Marc Mapeke · Andreas Meuleman · Matthew O'Toole · Mikhail Okunev · Christian Richardt · Aarrushi Shandilya

Papers in this thread

TöRF: Time-of-Flight Radiance Fields for Dynamic Scene View Synthesis
Neural Information Processing Systems (NeurIPS), 2021
Establishes that a 4D scene can be supervised directly by continuous-wave ToF phasor measurements rather than processed depth, with added colour cameras, showing low noise, super-resolution, and better multi-path handling.
Flowed Time of Flight Radiance Fields
European Conference on Computer Vision (ECCV), 2024
Adds motion vectors that are jointly estimated with geometry. Uses four raw frames (not phasors) captured over time from a continuous-wave ToF sensor to create a coherent dynamic reconstruction. 20× less depth error on dynamic objects than the C-ToF baseline.
Time of the Flight of the Gaussians: Optimizing Depth Indirectly in Dynamic Radiance Fields
Computer Vision and Pattern Recognition (CVPR), 2025
Applies raw ToF supervision to a Gaussian splatting backbone, with two heuristics that stabilise the otherwise-brittle 3DGS optimisation when depth is not directly measured. Comparable quality to neural volumetric baselines while training ~100× faster.

Related papers

Neural Fields for Structured Lighting
International Conference on Computer Vision (ICCV), 2023
Carries the supervision-by-raw-measurement approach from ToF over to structured light, and lets us separate direct and ambient illumination. Recovers higher-fidelity depth on objects than commodity structured light sensors, including for partially-transparent surfaces.
FloatingFusion: Depth from ToF and Image-stabilized Stereo Cameras
European Conference on Computer Vision (ECCV), 2022
Fuses ToF depth with stereo from a smartphone's optically-stabilised main RGB camera, where the floating lens has unknown pose. Self-calibrates the multi-sensor geometry from a single snapshot, then fuses via a correlation volume.
Controllable Generative Models
How do we efficiently control generative models to produce what we want—preserving identity, 3D structure, style—without sacrificing quality?
2018–now

Controllable Generative Models

How do we efficiently control generative models to produce what we want—preserving identity, 3D structure, style—without sacrificing quality?

A generative model that can sample new content is impressive; one that produces exactly what a user has in mind is useful. Controlling generation requires aligning the model's latent structure with axes a person can articulate—identity, pose, style, lighting, geometry—without sacrificing the photorealism that brought the model to relevance in the first place. There is usually a quality-versus-control tradeoff to manage.

This thread runs from Youssef Mejjati's PhD work on unsupervised attention for image-to-image translation, through compositional controls (object stamps, GaussiGAN's 3D Gaussian primitives from silhouettes alone), into 3DMM-conditioned face generation where Yiwen Huang's PhD now sits. Two recent moves matter: TaxFreeGAN closes the FID gap to unconditional StyleGAN under 3DMM conditioning, and our disentangling-3D work shows that the noise in CLIP's embedding space—not the disentanglement strategy—is what kills quality. R3GAN sits alongside this arc as our architectural reset: a principled relativistic loss that lets the modern GAN drop its bag of tricks.

Authors

Akin Caliskan · Darren Cosker · Aaron Gokaslan · Yiwen Huang · Berkay Kicanaoglu · Hyeongwoo Kim · Kwang In Kim · Atsunobu Kotani · Volodymyr Kuleshov · Youssef A. Mejjati · Isa Milefchik · Christian Richardt · Zejiang Shen · Michael Snower · Stefanie Tellex · Vikas Thamizharasan · Oliver Wang · Yue Wang · Xinjie Yi · Zhiqiu Yu · Qian Zhang

Papers in this thread

Unsupervised Attention-guided Image-to-Image Translation
Neural Information Processing Systems (NeurIPS), 2018
Jointly trains attention with generators and discriminators so unsupervised image-to-image translation can localise edits to objects without disturbing background or inter-object structure.
Generating Handwriting via Decoupled Style Descriptors
European Conference on Computer Vision (ECCV), 2020
Factors handwriting style into separate character-level and writer-level descriptors, letting the model generate new characters in a held-out writer's hand from only a few samples.
Generating Object Stamps
AI for Content Creation (AI4CC) @ CVPR, 2020
Splits conditional object insertion into a mask generator (shape, given a class and bounding box) and a texture generator (appearance, conditioned on the background), so the inserted object is both diverse in shape and consistent with its surroundings.
GaussiGAN: Controllable Image Synthesis with 3D Gaussians from Unposed Silhouettes
British Machine Vision Conference (BMVC) + AI for Content Creation (AI4CC) @ CVPR, 2021
Learns a coarse 3D object representation as a set of self-supervised anisotropic 3D Gaussians from unposed 2D masks alone, then uses it to drive controllable mask and texture synthesis with interactive posing.
Learning Physically-based Material and Lighting Decompositions for Face Editing
International Conference on Computational Visual Media (CVM), 2022
Estimates per-portrait surface normals, albedo, roughness, and a high-frequency lighting map, and decomposes diffuse and specular reflectance—so a downstream editor can relight a face from a single photograph.
Removing the Quality Tax in Controllable Face Generation
Winter Conference on Applications of Computer Vision (WACV) + AI for Content Creation (AI4CC) @ CVPR, 2024
Formalises 3DMM-conditioned face generation as a maths problem, then applies targeted fixes that close the FID gap to unconditional StyleGAN—so controllability no longer costs visible image quality.
Disentangling 3D from Large Vision-Language Models for Controlled Portrait Generation
2025
Disentangles 3D portrait generation from a frozen CLIP plus a FLAME morphable model, then identifies CLIP's noisy embedding directions as the residual source of entanglement and damps them with a stochastic Jacobian regulariser.
The GAN is Dead; Long Live the GAN! A Modern GAN Baseline
Neural Information Processing Systems (NeurIPS), 2024
A regularised relativistic GAN loss with proven local convergence lets a minimalist StyleGAN2-derived architecture—stripped of the usual stabilisation tricks—beat StyleGAN2 on FFHQ, ImageNet, CIFAR, and Stacked MNIST, and compete with diffusion models.
Light Fields—from Display to 4D Algorithms
The light field is a 4D record of a scene's rays—how do we present it to humans, interact with it, and process it computationally?
2012–2021

Light Fields—from Display to 4D Algorithms

The light field is a 4D record of a scene's rays—how do we present it to humans, interact with it, and process it computationally?

A light field captures the radiance at every point in space, in every direction—a 4D function that fully describes how light fills a scene. Captured light fields enable refocusing, depth recovery, and parallax view synthesis; displayed light fields offer glasses-free 3D. The challenge is data density: 4D content stresses capture devices, display hardware, and processing pipelines.

Two sub-arcs sit in this thread. In the first (2012–2015), I targeted light field displays—an Emerging Technologies demo of painting directly into a glasses-free 3D display, content-adaptive lenticular prints that reshape the lenslet array to the captured light field, and a UIST paper that turns that lenslet array into a joint display-and-pen-input surface. In the second (2019–2021), Numair Khan and I, with Min H. Kim at KAIST, developed algorithms for dense estimation over captured 4D content: view-consistent superpixels via epipolar-plane image segmentation, edge-aware bidirectional diffusion for depth, and a differentiable diffusion routine for sparse-to-dense depth from multi-view images.

Authors

Marc Alexa · Simon Heinzle · Stanislav Jakuschevskij · Lucas Kasser · Jan Kautz · Numair Khan · Min H. Kim · Wojciech Matusik · James McCann · Jim McCann · Samuel Muff · Hanspeter Pfister · Henry Stone · Qian Zhang

Papers in this thread

Interactive Light Field Painting
SIGGRAPH Emerging Technologies, 2012
An early SIGGRAPH Emerging Technologies demo of a dual-purpose lenslet array that both displays a light field and senses a 3D light-pen position—the live precursor to the UIST 2015 write-up.
Content-adaptive Lenticular Prints
Transactions on Graphics (SIGGRAPH), 2013
Treats the lenslet array as something to optimise rather than fix in advance—given an input light field, solve for lenslet size, shape, and arrangement that trade spatial against angular resolution where it matters. Validated by 3D printing the resulting arrays.
Joint 5D Pen Input for Light Field Displays
User Interface Software and Technology (UIST), 2015
One lenslet array does double duty—light field output and 5D pen input (3D position plus 2D orientation) at 150 Hz, with millimetre-scale accuracy. The display surface and the input surface are the same surface.
View-consistent 4D Light Field Superpixel Segmentation
International Conference on Computer Vision (ICCV), 2019
Segments horizontal and vertical EPIs first, then clusters and propagates across all sub-aperture views—so superpixels stay consistent and respect occlusion as the viewpoint shifts, rather than being propagated outwards from a single central view.
Differentiable Diffusion for Dense Depth Estimation from Multi-view Images
Computer Vision and Pattern Recognition (CVPR), 2021
Dense depth is obtained by diffusing a sparse set of points whose positions, depths, and weights are differentiably optimised through Gaussian splatting against a multi-view RGB reprojection loss. Scales to the 50k+ points needed for non-trivial scenes.
Edge-aware Bidirectional Diffusion for Dense Depth Estimation from Light Fields
British Machine Vision Conference (BMVC), 2021
Sparse EPI-derived edges diffused into dense depth via bidirectional diffusion, with the diffusion direction guided to separate depth edges from texture edges.
View-consistent 4D Light Field Depth Estimation
British Machine Vision Conference (BMVC), 2020
Central-view depth propagated to every other sub-aperture view in an occlusion-aware way, with disoccluded regions completed by EPI-space diffusion.
Editing Video by Recovering Scene Structure
How do we let users edit captured video meaningfully—by first recovering the scene structure (moving objects, lighting vs reflectance, cross-frame consistency) that makes plausible modifications possible?
2011–2017

Editing Video by Recovering Scene Structure

How do we let users edit captured video meaningfully—by first recovering the scene structure (moving objects, lighting vs reflectance, cross-frame consistency) that makes plausible modifications possible?

Editing video is harder than editing a photograph: changes to one frame must propagate consistently to every other, and many edits (removing a person, separating lighting from material, stabilising flicker) require understanding the underlying scene rather than just manipulating pixels. We approach editing as inverse reconstruction: decompose video into scene structure first, then edit.

This thread spans my doctoral and postdoc years across UCL, MPI-Inf, Harvard, and LIRIS-CNRS. My earliest piece (2011, UCL) is the cinemagraphs authoring tool—a moment image isolated from a stabilised clip. Miguel Granados led the video-inpainting work at MPI-Inf (2012)—removing dynamic objects from crowded scenes, and the harder case of background recovery under a free-moving camera. Nicolas Bonneel led the consistency and decomposition line (2014–2017)—interactive intrinsic decomposition, blind temporal consistency stabilising any per-frame filter, and the spatio-temporal extension to camera arrays. Our 2016 multicut paper takes a different angle on the same theme: cut the video into the right regions before editing.

Authors

Bjoern Andres · Nicolas Bonneel · Miguel Granados · Oliver Grau · Jan Kautz · Kwang In Kim · Steffen Kirchhoff · Evgeny Levinkov · Sylvain Paris · Fabrizio Pece · Hanspeter Pfister · Kartic Subr · Kalyan Sunkavalli · Deqing Sun · Christian Theobalt · Oliver Wang

Papers in this thread

Towards Moment Imagery: Automatic Cinemagraphs
European Conference on Visual Media Production (CVMP), 2011
An authoring tool that pipelines stabilisation, segmentation, motion selection, and loop detection to produce cinemagraphs—short looping clips where only a chosen region moves.
How Not to Be Seen — Object Removal from Videos of Crowded Scenes
Computer Graphics Forum (Eurographics), 2012
Object removal from crowded scenes by filling the spatio-temporal hole from other regions of the video where the occluded background was visible, posed as a graph-cut optimisation. Pitched at occlusions harder than previous work had attempted.
Background Inpainting for Videos with Dynamic Objects and a Free-moving Camera
European Conference on Computer Vision (ECCV), 2012
Inpaints background revealed by removing dynamic objects from a free-moving-camera video by aligning candidate frames with piecewise planar homographies—sidestepping the full per-frame depth and pose recovery that earlier free-camera methods required.
Interactive Intrinsic Video Editing
Transactions on Graphics (SIGGRAPH Asia), 2014
Decomposes video into reflectance and illumination via a hybrid L2-Lp gradient split, fast enough (two orders of magnitude over prior tools) to support interactive refinement and lighting-aware compositing.
Blind Video Temporal Consistency
Transactions on Graphics (SIGGRAPH Asia), 2015
A gradient-domain post-process that stabilises any per-frame filter against flicker by borrowing temporal regularity from the unprocessed video—agnostic to what the filter actually is. Demonstrated across stylisation, intrinsic decomposition, and depth.
Interactive Multicut Video Segmentation
Pacific Graphics (Short Paper), 2016
Interactive multi-label video segmentation from multi-coloured scribbles, posed as a multicut on a supervoxel graph and solved fast enough to feel responsive. Multiple objects cut at once with consistent spatio-temporal boundaries, rather than chained binary segmentations.
Consistent Video Filtering for Camera Arrays
Computer Graphics Forum (Eurographics), 2017
Extends the blind-consistency idea from time to time-and-space across stereo, light field, and wide-baseline rigs, and adds a filter-transfer scheme that runs the expensive filter on a small subset of frames and propagates the effect—an order-of-magnitude saving for camera-array data.

Splat-based Gradient-domain Fusion for Seamless View Transition
Dongyoung Choi, Jaemin Cho, Woohyun Kang, Hyunho Ha, James Tompkin, Min H. Kim
International Conference on 3D Vision (3DV), 2026
Thread: Practical Scene & Object Reconstruction
TreeDGS: Aerial Gaussian Splatting for Distant DBH Measurement
Belal Shaheen, Minh-Hieu Nguyen, Bach-Thuan Bui, Shubham, Tim Wu, Michael Fairley, Matthew David Zane, Michael Wu, James Tompkin
MDPI Remote Sensing, 2026
Thread: Practical Scene & Object Reconstruction
Efficient Object Reconstruction with Differentiable Area Light Shading
Yaoan Gao, Jiamin Xu, James Tompkin, Qi Wang, Zheng Dong, Hujun Bao, Yujun Shen, Huamin Wang, Changqing Zou, Weiwei Xu
SIGGRAPH Asia Conference Papers, 2025
Thread: Practical Scene & Object Reconstruction
InfoVids: Reimagining the Viewer Experience with Alternative Visualization-Presenter Relationships
Ji Won Chung, Tongyu Zhou, Ivy Chen, Kevin Hsu, Ryan A. Rossi, Alexa Siu, Shunan Guo, Franck Dernoncourt, James Tompkin, Jeff Huang
2025
Zero-Shot Monocular Scene Flow Estimation in the Wild
Yiqing Liang, Abhishek Badki, Hang Su, James Tompkin, Orazio Gallo
Computer Vision and Pattern Recognition (CVPR), 2025
Thread: Monocular Dynamic 3D Reconstruction
Time of the Flight of the Gaussians: Optimizing Depth Indirectly in Dynamic Radiance Fields
Runfeng Li, Mikhail Okunev, Zixuan Guo, Anh Duong, Christian Richardt, Matthew O'Toole, James Tompkin
Computer Vision and Pattern Recognition (CVPR), 2025
Thread: Active Illumination for Dynamic 3D Reconstruction
Local Gaussian Density Mixtures for Unstructured Lumigraph Rendering
Xiuchao Wu, Jiamin Xu, Chi Wang, Yifan Peng, Qixing Huang, James Tompkin, Weiwei Xu
SIGGRAPH Asia Conference Papers, 2024
Thread: Practical Scene & Object Reconstruction
The GAN is Dead; Long Live the GAN! A Modern GAN Baseline
Yiwen Huang, Aaron Gokaslan, Volodymyr Kuleshov, James Tompkin
Neural Information Processing Systems (NeurIPS), 2024
OpenReview (public reviews and response)
Thread: Controllable Generative Models
Monocular Dynamic Gaussian Splatting: Fast, Brittle, and Scene Complexity Rules
Yiqing Liang, Mikhail Okunev, Mikaela Angelina Uy, Runfeng Li, Leonidas J. Guibas, James Tompkin, Adam Harley
Transactions on Machine Learning Research (TMLR), 2025
Thread: Monocular Dynamic 3D Reconstruction
Flowed Time of Flight Radiance Fields
Mikhail Okunev, Marc Mapeke, Benjamin Attal, Christian Richardt, Matthew O'Toole, James Tompkin
European Conference on Computer Vision (ECCV), 2024
Thread: Active Illumination for Dynamic 3D Reconstruction
Active Appearance and Spatial Variation Can Improve Visibility in Area Labels for Augmented Reality
Hojung Kwon, Yuanbo Li, Xiaohan Ye, Praccho Muna-McQuay, Liuren Yin, James Tompkin
Transactions on Visualization and Computer Graphics (IEEE Visualization Short Paper), 2024
OmniSDF: Scene Reconstruction using Omnidirectional Signed Distance Functions and Adaptive Binoctrees
Hakyeong Kim, Andreas Meuleman, Hyeonjoong Jang, James Tompkin, Min H. Kim
Computer Vision and Pattern Recognition (CVPR), 2024
Thread: Practical Scene & Object Reconstruction
Disentangling 3D from Large Vision-Language Models for Controlled Portrait Generation
Yiwen Huang, Akin Caliskan, Berkay Kicanaoglu, James Tompkin, Hyeongwoo Kim
2025
Gives insight into why disentangling with CLIP is difficult—it's the prompt noise!
Thread: Controllable Generative Models
Removing the Quality Tax in Controllable Face Generation
Yiwen Huang, Zhiqiu Yu, Xinjie Yi, Yue Wang, James Tompkin
Winter Conference on Applications of Computer Vision (WACV) + AI for Content Creation (AI4CC) @ CVPR, 2024
Thread: Controllable Generative Models
GauFRe🧇: Gaussian Deformation Fields for Real-time Dynamic Novel View Synthesis
Yiqing Liang, Numair Khan, Zhengqin Li, Thu Nguyen-Phuoc, Douglas Lanman, James Tompkin, Lei Xiao
arXiv (Dec. 2023) + WACV, 2025
Thread: Monocular Dynamic 3D Reconstruction
ScaNeRF: Scalable Bundle-Adjusting Neural Radiance Fields for Large-Scale Scene Rendering
Xiuchao Wu, Jiamin Xu, Xin Zhang, Hujun Bao, Qixing Huang, Yujun Shen, James Tompkin, Weiwei Xu
Transactions on Graphics (SIGGRAPH Asia), 2023
Thread: Practical Scene & Object Reconstruction
Semantic Attention Flow Fields for Monocular Dynamic Scene Decomposition
Yiqing Liang, Eliot Laidlaw, Alexander Meyerowitz, Srinath Sridhar, James Tompkin
International Conference on Computer Vision (ICCV), 2023
Thread: Monocular Dynamic 3D Reconstruction
Neural Fields for Structured Lighting
Aarrushi Shandilya, Benjamin Attal, Christian Richardt, James Tompkin, Matthew O'Toole
International Conference on Computer Vision (ICCV), 2023
Thread: Active Illumination for Dynamic 3D Reconstruction
Are Multi-view Edges Incomplete for Depth Estimation?
Numair Khan, Min H. Kim, James Tompkin
International Journal of Computer Vision (IJCV), 2024
On Human-like Biases in Convolutional Neural Networks for the Perception of Slant from Texture
Yuanhao Wang, Qian Zhang, Celine Aubuchon, Jovan Kemp, Fulvio Domini, James Tompkin
Transactions on Applied Perception (TAP), 2023
How Can Deep Neural Networks Aid Visualization Perception Research? Three Studies on Correlation Judgments in Scatterplots
Fumeng Yang, Yuxin Ma, Lane Harrison, James Tompkin, David H. Laidlaw
Conference on Human Factors in Computing Systems (CHI), 2023
Learning Vector Quantized Shape Code for Amodal Blastomere Instance Segmentation
Won-Dong Jang, Donglai Wei, Xingxuan Zhang, Brian Leahy, Helen Yang, James Tompkin, Dalit Ben-Yosef, Daniel Needleman, Hanspeter Pfister
International Symposium on Biomedical Imaging (ISBI), 2023
Scalable Neural Indoor Scene Rendering
Xiuchao Wu, Jiamin Xu, Zihan Zhu, Hujun Bao, Qixing Huang, James Tompkin, Weiwei Xu
Transactions on Graphics (SIGGRAPH), 2022
Thread: Practical Scene & Object Reconstruction
Neural Fields in Visual Computing and Beyond
Yiheng Xie, Towaki Takikawa, Shunsuke Saito, Or Litany, Shiqin Yan, Numair Khan, Federico Tombari, James Tompkin, Vincent Sitzmann, Srinath Sridhar
Eurographics State of the Art Report + CVPR Tutorial + SIGGRAPH Course, 2022
FloatingFusion: Depth from ToF and Image-stabilized Stereo Cameras
Andreas Meuleman, Hakyeong Kim, James Tompkin, Min H. Kim
European Conference on Computer Vision (ECCV), 2022
Thread: Active Illumination for Dynamic 3D Reconstruction
Differentiable Appearance Acquisition from a Flash/No-flash RGB-D Pair
Hyun Jin Ku, Hyunho Ha, Joo Ho Lee, Dahyun Kang, James Tompkin, Min H. Kim
International Conference on Computational Photography (ICCP), 2022
Dually Noted: Layout-Aware Annotations with Smartphone Augmented Reality
Jing Qian, Qi Sun, Curtis Wigington, Han L. Han, Tong Sun, Jennifer Healey, James Tompkin, Jeff Huang
Conference on Human Factors in Computing Systems (CHI), 2022
YouMVOS: An Actor-centric Multi-shot Video Object Segmentation Dataset
Donglai Wei, Siddhant Kharbanda, Sarthak Arora, Roshan Roy, Nishant Jain, Akash Palrecha, Tanav Shah, Shray Mathur, Ritik Mathur, Abhijay Kemkar, Anirudh Chakravarthy, Zudi Lin, Won-Dong Jang, Yansong Tang, Song Bai, James Tompkin, Philip H.S. Torr, Hanspeter Pfister
Computer Vision and Pattern Recognition (CVPR), 2022
Dynamic Scene Novel View Synthesis via Deferred Spatio-temporal Consistency
Beatrix-Emőke Fülöp-Balogh, Eleanor Tursman, James Tompkin, Nicolas Bonneel, Julie Digne
Computers & Graphics, 2022
For recovering depth, this follows up Blind Video Spatio-Temporal Consistency and Blind Video Temporal Consistency.
Learning Physically-based Material and Lighting Decompositions for Face Editing
Qian Zhang, Vikas Thamizharasan, James Tompkin
International Conference on Computational Visual Media (CVM), 2022
Also appeared at AI for Content Creation (AI4CC) @ CVPR 2021.
Thread: Controllable Generative Models
Visual Cue Effects on a Classification Accuracy Estimation Task in Immersive Scatterplots
Fumeng Yang, James Tompkin, Lane Harrison, David H. Laidlaw
Transactions on Visualization and Computer Graphics (TVCG), 2022
Hosted at the Open Science Foundation.
TöRF: Time-of-Flight Radiance Fields for Dynamic Scene View Synthesis
Benjamin Attal, Eliot Laidlaw, Aaron Gokaslan, Changil Kim, Christian Richardt, James Tompkin, Matthew O'Toole
Neural Information Processing Systems (NeurIPS), 2021
Thread: Active Illumination for Dynamic 3D Reconstruction
Testing using Privileged Information by Adapting Features with Statistical Dependence
Kwang In Kim, James Tompkin
International Conference on Computer Vision (ICCV), 2021
Differentiable Diffusion for Dense Depth Estimation from Multi-view Images
Numair Khan, Min H. Kim, James Tompkin
Computer Vision and Pattern Recognition (CVPR), 2021
Thread: Light Fields—from Display to 4D Algorithms
GaussiGAN: Controllable Image Synthesis with 3D Gaussians from Unposed Silhouettes
Youssef A. Mejjati, Isa Milefchik, Aaron Gokaslan, Oliver Wang, Kwang In Kim, James Tompkin
British Machine Vision Conference (BMVC) + AI for Content Creation (AI4CC) @ CVPR, 2021
Thread: Controllable Generative Models
Scalable Scalable Vector Graphics: Automatic Translation of Interactive SVGs to a Multithread VDOM for Fast Rendering
Michail Schwab, David Saffo, Nicholas Bond, Shash Sinha, Cody Dunne, Jeff Huang, James Tompkin, Michelle A. Borkin
Transactions on Visualization and Computer Graphics (TVCG), 2021
MatryODShka: Real-time 6DoF Video View Synthesis using Multi-Sphere Images
Benjamin Attal, Selena Ling, Aaron Gokaslan, Christian Richardt, James Tompkin
European Conference on Computer Vision (ECCV), 2020
Generating Handwriting via Decoupled Style Descriptors
Atsunobu Kotani, Stefanie Tellex, James Tompkin
European Conference on Computer Vision (ECCV), 2020
Thread: Controllable Generative Models
Edge-aware Bidirectional Diffusion for Dense Depth Estimation from Light Fields
Numair Khan, Min H. Kim, James Tompkin
British Machine Vision Conference (BMVC), 2021
Thread: Light Fields—from Display to 4D Algorithms
View-consistent 4D Light Field Depth Estimation
Numair Khan, Min H. Kim, James Tompkin
British Machine Vision Conference (BMVC), 2020
Thread: Light Fields—from Display to 4D Algorithms
Shape from Tracing: Towards Reconstructing 3D Object Geometry and SVBRDF Material from Images via Differentiable Path Tracing
Purvi Goel, Loudon Cohen, James Guesman, Vikas Thamizharasan, James Tompkin, Daniel Ritchie
International Conference on 3D Vision (3DV), 2020
Thread: Practical Scene & Object Reconstruction
Capture, Reconstruction, and Representation of the Visual Real World for Virtual Reality
Christian Richardt, James Tompkin, Gordon Wetzstein
Real VR – Immersive Digital Reality, 2020
Chapter in the Real VR – Immersive Digital Reality Springer book; DOI.
VisConnect: Distributed Event Synchronization for Collaborative Visualization
Michail Schwab, David Saffo, Yixuan Zhang, Shash Sinha, Cristina Nita-Rotaru, James Tompkin, Cody Dunne, Michelle A. Borkin
Transactions on Visualization and Computer Graphics (IEEE Visualization), 2020
Channel Embedding for Informative Protein Identification from Highly Multiplexed Images
Salma A. Magid, Won-Dong Jang, Denis Schapiro, Donglai Wei, James Tompkin, Peter Sorger, Hanspeter Pfister
Medical Image Computing and Computer-Assisted Intervention (MICCAI), 2020
View-consistent 4D Light Field Superpixel Segmentation
Numair Khan, Qian Zhang, Lucas Kasser, Henry Stone, Min H. Kim, James Tompkin
International Conference on Computer Vision (ICCV), 2019
This work also produces an occlusion-aware piecewise planar scene reconstruction as a byproduct!
Thread: Light Fields—from Display to 4D Algorithms
Portal-ble: Intuitive Free-hand Manipulation in Unbounded Smartphone-based Augmented Reality
Jing Qian, Jiaju Ma, Xiangyu Li, Benjamin Attal, Haoming Lai, James Tompkin, John F. Hughes, Jeff Huang
User Interface Software and Technology (UIST), 2019
Real-time Virtual Object Insertion for Moving 360° Videos
Joanna Tarko, James Tompkin, Christian Richardt
International Conference on Virtual-Reality Continuum and its Applications in Industry (VRCAI), 2019
DOI: 10.1145/3359997.3365708
Evaluating Pan and Zoom Timelines and Sliders
Michail Schwab, Sicheng Hao, Olga Vitek, James Tompkin, Jeff Huang, Michelle A. Borkin
Conference on Human Factors in Computing Systems (CHI), 2019
EasyPZ.js: Interaction Binding for Pan and Zoom Visualizations
Michail Schwab, James Tompkin, Jeff Huang, Michelle A. Borkin
Transactions on Visualization and Computer Graphics (IEEE Visualization Short Paper), 2019
One-line SVG pan/zoom, plus a pan/zoom injecting bookmark for any SVG! The project page hosts docs, jsFiddle, and bl.ocks.org examples.
Communicating and Controlling Robot Arm Motion Intent Through Mixed Reality Head-mounted Displays
Eric Rosen, David Whitney, Elizabeth Phillips, Gary Chien, James Tompkin, George Konidaris, Stefanie Tellex
International Journal of Robotics Research (IJRR), 2019
Unsupervised Attention-guided Image-to-Image Translation
Youssef A. Mejjati, Christian Richardt, James Tompkin, Darren Cosker, Kwang In Kim
Neural Information Processing Systems (NeurIPS), 2018
Thread: Controllable Generative Models
Improving Shape Deformation in Unsupervised Image-to-Image Translation
Aaron Gokaslan, Vivek Ramanujan, Daniel Ritchie, Kwang In Kim, James Tompkin
European Conference on Computer Vision (ECCV), 2018
Evaluating 'Graphical Perception' with CNNs
Daniel Haehn, James Tompkin, Hanspeter Pfister
Transactions on Visualization and Computer Graphics (IEEE Visualization), 2018
Project page bundles the paper, code, and data.
Guided Proofreading of Automatic Segmentations for Connectomics
Daniel Haehn, Verena Kaynig, James Tompkin, Jeff W. Lichtman, Hanspeter Pfister
Computer Vision and Pattern Recognition (CVPR), 2018
High-order Tensor Regularization with Application to Attribute Ranking
Kwang In Kim, Juhyun Park, James Tompkin
Computer Vision and Pattern Recognition (CVPR), 2018
Supplemental PDF
The Eye of the Typer: A Benchmark and Analysis of Gaze Behavior during Typing
Alexandra Papoutsaki, Aaron Gokaslan, James Tompkin, Yuze He, Jeff Huang
Symposium on Eye Tracking Research and Applications (ETRA), 2018
Project page bundles paper and code; dataset is hosted separately.
Criteria Sliders: Learning Continuous Database Criteria via Interactive Ranking
James Tompkin, Kwang In Kim, Hanspeter Pfister, Christian Theobalt
British Machine Vision Conference (BMVC), 2017
Consistent Video Filtering for Camera Arrays
Nicolas Bonneel, James Tompkin, Deqing Sun, Oliver Wang, Kalyan Sunkavalli, Sylvain Paris, Hanspeter Pfister
Computer Graphics Forum (Eurographics), 2017
We could have called it Blind Video Spatio-Temporal Consistency as it follows up Blind Video Temporal Consistency.
Thread: Editing Video by Recovering Scene Structure
Predictor Combination at Test Time
Kwang In Kim, James Tompkin, Christian Richardt
International Conference on Computer Vision (ICCV), 2017
Supplemental PDF
Piggybacking Robots: Human-Robot Overtrust in University Dormitory Security
Serena Booth, James Tompkin, Krzysztof Gajos, Jim Waldo, Hanspeter Pfister, Radhika Nagpal
Conference on Human-Robot Interaction (HRI), 2017
Communicating Robot Arm Motion Intent Through Mixed Reality Head-mounted Displays
Eric Rosen, David Whitney, Elizabeth Phillips, Gary Chien, James Tompkin, George Konidaris, Stefanie Tellex
International Symposium on Robotics Research (ISRR), 2017
Scalable Interactive Visualization for Connectomics
Daniel Haehn, John Hoffer, Brian Matejek, Adi Suissa-Peleg, Ali K. Al-Awami, Lee Kamentsky, Felix Gonda, Eagon Meng, William Zhang, Richard Schalek, Alyssa Wilson, Toufiq Parag, Johanna Beyer, Verena Kaynig, Thouis R. Jones, James Tompkin, Markus Hadwiger, Jeff W. Lichtman, Hanspeter Pfister
MDPI Informatics—Special Issue on Scalable Interactive Visualization, 2017
booc.io: An Education System with Hierarchical Concept Maps and Dynamic Non-linear Learning Plans
Michail Schwab, Hendrik Strobelt, James Tompkin, Colin Fredericks, Connor Huff, Dana Higgins, Anton Strezhnev, Maya Komisarchik, Gary King, Hanspeter Pfister
Transactions on Visualization and Computer Graphics (IEEE Visualization), 2016
Interactive Multicut Video Segmentation
Evgeny Levinkov, James Tompkin, Nicolas Bonneel, Steffen Kirchhoff, Bjoern Andres, Hanspeter Pfister
Pacific Graphics (Short Paper), 2016
Thread: Editing Video by Recovering Scene Structure
Joint 5D Pen Input for Light Field Displays
James Tompkin, Samuel Muff, James McCann, Hanspeter Pfister, Jan Kautz, Marc Alexa, Wojciech Matusik
User Interface Software and Technology (UIST), 2015
Also at SIGGRAPH Emerging Technologies 2012: Interactive Light Field Painting
Thread: Light Fields—from Display to 4D Algorithms
Generalizing Wave Gestures from Sparse Examples for Real-time Character Control
Helge Rhodin, James Tompkin, Kwang In Kim, Edilson de Aguiar, Hanspeter Pfister, Hans-Peter Seidel, Christian Theobalt
Transactions on Graphics (SIGGRAPH Asia), 2015
Builds upon project: Direct Motion Mapping
Blind Video Temporal Consistency
Nicolas Bonneel, James Tompkin, Kalyan Sunkavalli, Deqing Sun, Sylvain Paris, Hanspeter Pfister
Transactions on Graphics (SIGGRAPH Asia), 2015
Related project: Blind Video Spatio-Temporal Consistency
Thread: Editing Video by Recovering Scene Structure
Computational Design of Metallophone Contact Sounds
Gaurav Bharaj, David I.W. Levin, James Tompkin, Yun Fei, Hanspeter Pfister, Wojciech Matusik, Changxi Zheng
Transactions on Graphics (SIGGRAPH Asia), 2015
Computational Design of Walking Automata
Gaurav Bharaj, Stelian Coros, Bernhard Thomaszewski, James Tompkin, Bernd Bickel, Hanspeter Pfister
Symposium on Computer Animation (SCA), 2015
Semi-supervised Learning with Explicit Relationship Regularization
Kwang In Kim, James Tompkin, Hanspeter Pfister, Christian Theobalt
Computer Vision and Pattern Recognition (CVPR), 2015
Context-guided Diffusion for Label Propagation on Graphs
Kwang In Kim, James Tompkin, Hanspeter Pfister, Christian Theobalt
International Conference on Computer Vision (ICCV), 2015
Local High-order Regularization on Data Manifolds
Kwang In Kim, James Tompkin, Hanspeter Pfister, Christian Theobalt
Computer Vision and Pattern Recognition (CVPR), 2015
Interactive Intrinsic Video Editing
Nicolas Bonneel, Kalyan Sunkavalli, James Tompkin, Deqing Sun, Sylvain Paris, Hanspeter Pfister
Transactions on Graphics (SIGGRAPH Asia), 2014
Paper | Video
Thread: Editing Video by Recovering Scene Structure
Efficient Learning of Image Super-resolution and Compression Artifact Removal with Semi-local Gaussian Processes
Younghee Kwon, Kwang In Kim, James Tompkin, Jin Hyung Kim, Christian Theobalt
Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2014
Device Effect on Panoramic Video+Context Tasks
Fabrizio Pece, James Tompkin, Hanspeter Pfister, Jan Kautz, Christian Theobalt
European Conference on Visual Media Production (CVMP), 2014
Related project: Vidicontexts
Interactive Motion Mapping for Real-time Character Control
Helge Rhodin, James Tompkin, Kwang In Kim, Kiran Varanasi, Hans-Peter Seidel, Christian Theobalt
Computer Graphics Forum (Eurographics), 2014
Related project: Generalized Wave Gestures
Automatic Noise Modeling for Ghost-free HDR Reconstruction
Miguel Granados, Kwang In Kim, James Tompkin, Christian Theobalt
Transactions on Graphics (SIGGRAPH Asia), 2013
Curvature-aware Regularization on Riemannian Submanifolds
Kwang In Kim, James Tompkin, Christian Theobalt
International Conference on Computer Vision (ICCV), 2013
Code
Video Collections in Panoramic Contexts
James Tompkin, Fabrizio Pece, Rajvi Shah, Shahram Izadi, Jan Kautz, Christian Theobalt
User Interface Software and Technology (UIST), 2013
Related study into display device effect: Device Effect on Panoramic Video+Context Tasks
Preference and Artifact Analysis for Video Transitions of Places
James Tompkin, Min H. Kim, Kwang In Kim, Jan Kautz, Christian Theobalt
Transactions on Applied Perception (TAP), 2013
Content-adaptive Lenticular Prints
James Tompkin, Simon Heinzle, Jan Kautz, Wojciech Matusik
Transactions on Graphics (SIGGRAPH), 2013
Printing light field displays with varying spatio-angular resolution.
Thread: Light Fields—from Display to 4D Algorithms
Exploring Sparse Unstructured Video Collections of Places
James Tompkin
EngD Thesis @ University College London, 2013
Also archived at UCL Discovery. Related projects: Videoscapes, Transition Analysis, Match Graph Construction.
Interactive Viewpoint Video Textures
Philippe Levieux, James Tompkin, Jan Kautz
European Conference on Visual Media Production (CVMP), 2012
Alt title: Light Field Video Textures
Background Inpainting for Videos with Dynamic Objects and a Free-moving Camera
Miguel Granados, Kwang In Kim, James Tompkin, Jan Kautz, Christian Theobalt
European Conference on Computer Vision (ECCV), 2012
Project page includes the dataset.
Thread: Editing Video by Recovering Scene Structure
Match Graph Construction for Large Image Databases
Kwang In Kim, James Tompkin, Martin Theobald, Jan Kautz, Christian Theobalt
European Conference on Computer Vision (ECCV), 2012
Useful for building correspondence graphs for image matching, e.g., in search or large-scale reconstruction. Supplemental material.
Code
Videoscapes: Exploring Sparse Unstructured Video Collections
James Tompkin, Kwang In Kim, Jan Kautz, Christian Theobalt
Transactions on Graphics (SIGGRAPH), 2012
Interactive Light Field Painting
James Tompkin, Samuel Muff, Stanislav Jakuschevskij, Jim McCann, Jan Kautz, Marc Alexa, Wojciech Matusik
SIGGRAPH Emerging Technologies, 2012
Early demo of our later UIST 2015 publication Joint 5D Pen Input for Light Field Displays. Demo project page also at MIT CDFG.
Thread: Light Fields—from Display to 4D Algorithms
How Not to Be Seen — Object Removal from Videos of Crowded Scenes
Miguel Granados, James Tompkin, Kwang In Kim, Oliver Grau, Jan Kautz, Christian Theobalt
Computer Graphics Forum (Eurographics), 2012
Project page includes the dataset.
Thread: Editing Video by Recovering Scene Structure
Interactive Multi-perspective Imagery from Photos and Videos
Henrik Lieng, James Tompkin, Jan Kautz
Computer Graphics Forum (Eurographics), 2012
Project page includes code and data.
Code
Video-based Characters: Creating New Human Performances from a Multi-view Video Database
Feng Xu, Yebin Liu, Carsten Stoll, James Tompkin, Gaurav Bharaj, Qionghai Dai, Hans-Peter Seidel, Jan Kautz, Christian Theobalt
Transactions on Graphics (SIGGRAPH), 2011
Towards Moment Imagery: Automatic Cinemagraphs
James Tompkin, Fabrizio Pece, Kartic Subr, Jan Kautz
European Conference on Visual Media Production (CVMP), 2011
Thread: Editing Video by Recovering Scene Structure
Novel P300 BCI Interfaces to Directly Select Physical and Virtual Objects
Beste F. Yuksel, Michael Donnerer, James Tompkin, Anthony Steed
International Brain-Computer Interface Conference (BCI), 2011
Poster
A Novel Brain-computer Interface using a Multi-touch Surface
Beste F. Yuksel, Michael Donnerer, James Tompkin, Anthony Steed
Conference on Human Factors in Computing Systems (CHI), 2010
DIY Design Process for Interactive Surfaces
Jennifer G. Sheridan, James Tompkin, Abel Maciel, George Roussos
British HCI Group Annual Conference on People and Computers (BCS-HCI), 2009
Webpage contains many projects and events! Schematics and WebGL model viewer!
Venues: A Networked Visual Instrument
James Tompkin
MSci Dissertation @ King's College London, 2006
Videos
Code

Workshops and Courses

AI for Content Creation
CVPR 2019–2025 Workshop

Physics-inspired 3D Vision and Imaging
CVPR 2025 Workshop

Neural Fields Beyond Conventional Cameras
ECCV 2024 Workshop

Neural Fields in Visual Computing
CVPR 2022 Tutorial + SIGGRAPH 2023 Course

New England Computer Vision Symposium
Brown 2019

Video for Virtual Reality
SIGGRAPH 2017 Course

User-centric Computational Videography
SIGGRAPH 2015 Course

University Courses

CSCI 1430—Introduction to Computer Vision
Brown University
2016–now.

CSCI 1290—Computational Photography
Brown University
2018–now.

CSCI 2951-I—Computer Vision for Graphics and Interaction
Brown University
2016–now.

CSCI 2000—Computer Science Research Methods or How to be a CS PhD Student
Brown University
2021 Fall.

CSCI 1950-N—2D Game Engines
Brown University
2017–now. Mentoring student-led course.

GISP 0002—NFTs, Blockchain, and Art, led by Ally Zhu and Nikolas Lazar
Brown University
2022 Spring.

CS171—Visualization
Harvard University
2016 Spring, 2015 Spring.

Computer Vision for Computer Graphics
Max-Planck-Institute for Informatics
2013 Summer.

Doctoral Students

Joel Salzman
2025–
Yiwen (Nick) Huang
2024–
Publications:
Hojung Ashley Kwon
2022–
Publications:
Mikhail Okunev
2021–
Publications:
Yiqing Liang
2021–2025
On to: Luma AI Research Scientist
Thesis: "Learning to See in Four Dimensions: A Path to Spatiotemporal Intelligence"
Publications:
Qian Zhang
2018–
Publications:
Numair Khan
2016–2021
On to: Meta Reality Labs Research Scientist
Thesis: "Are Multi-view Edges Incomplete?"
Publications:

Masters Students

Runfeng Li
2023–2025
On to: Rice PhD
Publications:
Marc Mapeke
2021–2024
On to: Meta Reality Labs
Publications:
Yiwen (Nick) Huang
2021–2023
On to: Brown PhD
Publications:
Vikas Thamizharasan
2020–2022
On to: UMass Amherst PhD
Publications:
Selena Ling
2019–2021
On to: UToronto PhD
Publications:
Eleanor Tursman
2016–2020
On to: US Congressional Innovation Scholar
Thesis: "Towards Camera Choreography: Physically-constrained Multi-camera Clustering"
Publications:
Purvi Goel
2018–2020
On to: Stanford PhD
Thesis: "Shape from Tracing: Reconstructing 3D Geometry and SVBRDF Material from Images via Differentiable Pathtracing"
Publications:
Michael Snower
2018–2020
On to: Facebook AI on VR/AR
Thesis: "Improving Unpaired Object Translation for Unaligned Domains"
Publications:
Ziyin (Martin) Ma
2018–2020
On to: Google
Thesis: "Fauxtoshop: Modeling Image Editing Operations with Kernel Prediction Networks and Parameter Blocks"
Zejiang Shen
2019–2020
On to: Allen Institute for AI Residency; MIT PhD
Publications:
Benjamin Attal
2017–2019
On to: CMU PhD
Publications:
Aaron Gokaslan
2017–2019
On to: Facebook AI Residency; Cornell PhD
Thesis: "Exploring the Spectrum of Mask Supervision for Unpaired Image-to-Image Translation"
Publications:

Undergraduate Students

Anika Bahl
2023–2024
Thesis: "Art, Agency, and Computers: Human Perceptions of Creativity in Artistic Processes That Use Computational Agents"
Troy Conklin
2022–2024
On to: General Dynamics
Thesis: "Deblurring Long Exposure Astrophotography with Neural Networks"
Yuanhao (Harry) Wang
2021–2023
On to: CMU Research Masters; UW PhD
Thesis: "On Human-like Biases in Deep Neural Networks for the Perception of Slant from Texture"
Publications:
Xinjie (Jayden) Yi
2022–2023
On to: Harvard Data Science Masters
Thesis: "Quality or Control: Why Not Both? Rethinking 3DMM-Conditional Face Generation"
Publications:
Zhiqiu (Jacob) Yu
2021–2023
On to: Harvard Computational Science and Engineering Masters
Thesis: "Towards Social Video Verification to Combat Deepfakes via Deep Learning"
Publications:
Eliot Laidlaw
2020–2022
On to: Common Sense Machines
Thesis: "Towards a More Object-Centric Dynamic Scene Reconstruction Model"
Publications:
Atsunobu Kotani
2017–2020
On to: UC Berkeley PhD
Publications:
Isa Milefchik
2019–2021
On to: Common Sense Machines
Thesis: "Interactive Image Synthesis Using a Latent 3D Gaussian Model"
Publications:
Henry Stone
2018–2020
Thesis: "Transparent Voxelized Geometry Representations for Machine Learning"
Publications:
Lucas Kasser
2018–2019
Thesis: "Lightfield Superpixel Segmentation and Segmentation-Based Editing"
Publications:
Vivek Ramanujan
2017–2018
On to: Allen Institute for AI Residency; UW PhD
Publications:

Extended Family PhDs

Hakyeong Kim
2022–2025
Publications:
Xiuchao Wu
2021–2025
On to: Alibaba
Publications:
Youssef A. Mejjati
2018–2021
On to: Synthesia
Publications:
Michail Schwab
2014–2020
On to: Google
Publications:
Daniel Haehn
2014–2019
On to: UMass Boston Faculty
Publications:
Gaurav Bharaj
2014–2017
On to: Reality Defender
Publications:

Biography (2024)

James Tompkin is an Associate Professor of Computer Science at Brown University. His research at the intersection of computer vision, computer graphics, and human-computer interaction helps develop new visual computing tools and experiences from cameras. For this, his lab creates techniques for 3D scene reconstruction from multi-camera systems and for dynamics. His doctoral work at University College London on large-scale video processing and exploration techniques led to creative exhibition work in the Museum of the Moving Image in New York City. Postdoctoral work at Max-Planck-Institute for Informatics and Harvard University helped create new methods to edit content within images and videos. Recent research has developed new techniques for low-level reconstruction of dynamic scenes, view synthesis for VR, and AI content editing and generation.

Academic lineage

Please find my research summary video from 2015—our newer lab work is on the 'Research' tab.


SIGGRAPH 50th—2023

I supported SIGGRAPH's 50th conference in 2023 as the chair of the Posters program, which was coincidentally running its 20th iteration too. Here's a meta-poster about the program's history and its outstanding contributors (low-res PNG).

Faculty and Tenure Application Materials

To share my experience, here is the material I sent to Brown to apply for a tenure-track assistant professor position in Dec. 2015.
CV (Sept. 2016)
Research Statement
Teaching Statement

Here is the material I used for my tenure case at Brown in Dec. 2023.
CV
Research Statement
Teaching Statement

Exhibitions

I supported the Discover program and club at Brown/RISD to pair arts and science students and put on an exhibition (2017–2021). I have also tried to contribute work myself.

Bad Art @ Brown, 2018
with Aaron Gokaslan and Vivek Ramanujan

Rear Window Augmented
with Jeff Desom

Museum of the Moving Image
New York City
7th November 2015 to 10th April 2016

ISCP
New York City
7–9th November 2014

Festival Imaginales
Epinal, France
26–29th May 2014

Luxembourg Film Festival
28th February to 9th March 2014