Search Results for author: James Tompkin

Found 36 papers, 13 papers with code

Disentangling 3D from Large Vision-Language Models for Controlled Portrait Generation

no code implementations16 Jun 2025 Nick Yiwen Huang, Akin Caliskan, Berkay Kicanaoglu, James Tompkin, Hyeongwoo Kim

We consider the problem of disentangling 3D from large vision-language models, which we show on generative 3D portraits.

3D geometry

MoDoMoDo: Multi-Domain Data Mixtures for Multimodal LLM Reinforcement Learning

no code implementations30 May 2025 Yiqing Liang, JieLin Qiu, Wenhao Ding, Zuxin Liu, James Tompkin, Mengdi Xu, Mengzhou Xia, Zhengzhong Tu, Laixi Shi, Jiacheng Zhu

Specifically, (1) We developed a multimodal RLVR framework for multi-dataset post-training by curating a dataset that contains different verifiable vision-language problems and enabling multi-domain online RL learning with different verifiable rewards; (2) We proposed a data mixture strategy that learns to predict the RL fine-tuning outcome from the data mixture distribution, and consequently optimizes the best mixture.

Zero-Shot Monocular Scene Flow Estimation in the Wild

no code implementations CVPR 2025 Yiqing Liang, Abhishek Badki, Hang Su, James Tompkin, Orazio Gallo

Large models have shown generalization across datasets for many low-level vision tasks, like depth estimation, but no such general models exist for scene flow.

Depth Estimation Prediction +2

The GAN is dead; long live the GAN! A Modern GAN Baseline

1 code implementation9 Jan 2025 Yiwen Huang, Aaron Gokaslan, Volodymyr Kuleshov, James Tompkin

There is a widely-spread claim that GANs are difficult to train, and GAN architectures in the literature are littered with empirical tricks.

Image Generation

Monocular Dynamic Gaussian Splatting is Fast and Brittle but Smooth Motion Helps

no code implementations5 Dec 2024 Yiqing Liang, Mikhail Okunev, Mikaela Angelina Uy, Runfeng Li, Leonidas Guibas, James Tompkin, Adam W. Harley

Gaussian splatting methods are emerging as a popular approach for converting multi-view image data into scene representations that allow view synthesis.

OmniSDF: Scene Reconstruction using Omnidirectional Signed Distance Functions and Adaptive Binoctrees

no code implementations CVPR 2024 Hakyeong Kim, Andreas Meuleman, Hyeonjoong Jang, James Tompkin, Min H. Kim

We present a method to reconstruct indoor and outdoor static scene geometry and appearance from an omnidirectional video moving in a small circular sweep.

GauFRe: Gaussian Deformation Fields for Real-time Dynamic Novel View Synthesis

no code implementations18 Dec 2023 Yiqing Liang, Numair Khan, Zhengqin Li, Thu Nguyen-Phuoc, Douglas Lanman, James Tompkin, Lei Xiao

Specifically, we propose a template set of 3D Gaussians residing in a canonical space, and a time-dependent forward-warping deformation field to model dynamic objects.

Inductive Bias NeRF +1

'Tax-free' 3DMM Conditional Face Generation

no code implementations22 May 2023 Yiwen Huang, Zhiqiu Yu, Xinjie Yi, Yue Wang, James Tompkin

This results in a new model that effectively removes the quality tax between 3DMM conditioned face GANs and the unconditional StyleGAN.

Face Generation

Semantic Attention Flow Fields for Monocular Dynamic Scene Decomposition

no code implementations ICCV 2023 Yiqing Liang, Eliot Laidlaw, Alexander Meyerowitz, Srinath Sridhar, James Tompkin

From video, we reconstruct a neural volume that captures time-varying color, density, scene flow, semantics, and attention information.

Clustering

Neural Fields for Structured Lighting

no code implementations ICCV 2023 Aarrushi Shandilya, Benjamin Attal, Christian Richardt, James Tompkin, Matthew O'Toole

We present an image formation model and optimization procedure that combines the advantages of neural radiance fields and structured light imaging.

FloatingFusion: Depth from ToF and Image-stabilized Stereo Cameras

no code implementations6 Oct 2022 Andreas Meuleman, Hakyeong Kim, James Tompkin, Min H. Kim

Fusing RGB stereo and ToF information is a promising direction to overcome these issues, but a key problem remains: to provide high-quality 2D RGB images, the main color sensor's lens is optically stabilized, resulting in an unknown pose for the floating lens that breaks the geometric relationships between the multimodal image sensors.

Neural Fields in Visual Computing and Beyond

1 code implementation22 Nov 2021 Yiheng Xie, Towaki Takikawa, Shunsuke Saito, Or Litany, Shiqin Yan, Numair Khan, Federico Tombari, James Tompkin, Vincent Sitzmann, Srinath Sridhar

Recent advances in machine learning have created increasing interest in solving visual computing problems using a class of coordinate-based neural networks that parametrize physical properties of scenes or objects across space and time.

3D Reconstruction Image Animation +1

Testing using Privileged Information by Adapting Features with Statistical Dependence

no code implementations ICCV 2021 Kwang In Kim, James Tompkin

Then, we empirically estimate and strengthen the statistical dependence between the initial noisy predictor and the additional features via manifold denoising.

Attribute Denoising

Dynamic Scene Novel View Synthesis via Deferred Spatio-temporal Consistency

no code implementations2 Sep 2021 Beatrix-Emőke Fülöp-Balogh, Eleanor Tursman, James Tompkin, Julie Digne, Nicolas Bonneel

Structure from motion (SfM) enables us to reconstruct a scene via casual capture from cameras at different viewpoints, and novel view synthesis (NVS) allows us to render a captured scene from a new viewpoint.

Novel View Synthesis

Edge-aware Bidirectional Diffusion for Dense Depth Estimation from Light Fields

1 code implementation7 Jul 2021 Numair Khan, Min H. Kim, James Tompkin

We present an algorithm to estimate fast and accurate depth maps from light fields via a sparse set of depth edges and gradients.

Depth Estimation

GaussiGAN: Controllable Image Synthesis with 3D Gaussians from Unposed Silhouettes

no code implementations24 Jun 2021 Youssef A. Mejjati, Isa Milefchik, Aaron Gokaslan, Oliver Wang, Kwang In Kim, James Tompkin

We present an algorithm that learns a coarse 3D representation of objects from unposed multi-view 2D mask supervision, then uses it to generate detailed mask and image texture.

Image Generation Object +1

Differentiable Diffusion for Dense Depth Estimation from Multi-view Images

1 code implementation CVPR 2021 Numair Khan, Min H. Kim, James Tompkin

We present a method to estimate dense depth by optimizing a sparse set of points such that their diffusion into a depth map minimizes a multi-view reprojection error from RGB supervision.

Depth Estimation

View-consistent 4D Light Field Depth Estimation

1 code implementation9 Sep 2020 Numair Khan, Min H. Kim, James Tompkin

Previous light field depth estimation methods typically estimate a depth map only for the central sub-aperture view, and struggle with view consistent estimation.

Depth Estimation

Generating Handwriting via Decoupled Style Descriptors

1 code implementation ECCV 2020 Atsunobu Kotani, Stefanie Tellex, James Tompkin

Instead, we introduce the Decoupled Style Descriptor (DSD) model for handwriting, which factors both character- and writer-level styles and allows our model to represent an overall greater space of styles.

MatryODShka: Real-time 6DoF Video View Synthesis using Multi-Sphere Images

1 code implementation ECCV 2020 Benjamin Attal, Selena Ling, Aaron Gokaslan, Christian Richardt, James Tompkin

Our approach is to simultaneously learn depth and disocclusions via a multi-sphere image representation, which can be rendered with correct 6DoF disparity and motion parallax in VR.

Generating Object Stamps

1 code implementation1 Jan 2020 Youssef Alami Mejjati, Zejiang Shen, Michael Snower, Aaron Gokaslan, Oliver Wang, James Tompkin, Kwang In Kim

We present an algorithm to generate diverse foreground objects and composite them into background images using a GAN architecture.

Diversity Object

Unsupervised Attention-guided Image-to-Image Translation

1 code implementation NeurIPS 2018 Youssef Alami Mejjati, Christian Richardt, James Tompkin, Darren Cosker, Kwang In Kim

Current unsupervised image-to-image translation techniques struggle to focus their attention on individual objects without altering the background or the way multiple objects interact within a scene.

Translation Unsupervised Image-To-Image Translation

Improving Shape Deformation in Unsupervised Image-to-Image Translation

4 code implementations ECCV 2018 Aaron Gokaslan, Vivek Ramanujan, Daniel Ritchie, Kwang In Kim, James Tompkin

Unsupervised image-to-image translation techniques are able to map local texture between two domains, but they are typically unsuccessful when the domains require larger shape change.

Semantic Segmentation Translation +1

Unsupervised Attention-guided Image to Image Translation

2 code implementations6 Jun 2018 Youssef A. Mejjati, Christian Richardt, James Tompkin, Darren Cosker, Kwang In Kim

Current unsupervised image-to-image translation techniques struggle to focus their attention on individual objects without altering the background or the way multiple objects interact within a scene.

Translation Unsupervised Image-To-Image Translation

High-Order Tensor Regularization With Application to Attribute Ranking

no code implementations CVPR 2018 Kwang In Kim, Juhyun Park, James Tompkin

When learning functions on manifolds, we can improve performance by regularizing with respect to the intrinsic manifold geometry rather than the ambient space.

Attribute Vocal Bursts Intensity Prediction

Predictor Combination at Test Time

no code implementations ICCV 2017 Kwang In Kim, James Tompkin, Christian Richardt

We present an algorithm for test-time combination of a set of reference predictors with unknown parametric forms.

Denoising Transfer Learning

Criteria Sliders: Learning Continuous Database Criteria via Interactive Ranking

no code implementations12 Jun 2017 James Tompkin, Kwang In Kim, Hanspeter Pfister, Christian Theobalt

Large databases are often organized by hand-labeled metadata, or criteria, which are expensive to collect.

Guided Proofreading of Automatic Segmentations for Connectomics

no code implementations CVPR 2018 Daniel Haehn, Verena Kaynig, James Tompkin, Jeff W. Lichtman, Hanspeter Pfister

Automatic cell image segmentation methods in connectomics produce merge and split errors, which require correction through proofreading.

Image Segmentation Segmentation +1

Context-guided diffusion for label propagation on graphs

no code implementations ICCV 2015 Kwang In Kim, James Tompkin, Hanspeter Pfister, Christian Theobalt

Existing approaches for diffusion on graphs, e. g., for label propagation, are mainly focused on isotropic diffusion, which is induced by the commonly-used graph Laplacian regularizer.

Semi-supervised Learning with Explicit Relationship Regularization

no code implementations CVPR 2015 Kwang In Kim, James Tompkin, Hanspeter Pfister, Christian Theobalt

In many learning tasks, the structure of the target space of a function holds rich information about the relationships between evaluations of functions on different data points.

Constrained Clustering Dimensionality Reduction +1

Local High-order Regularization on Data Manifolds

no code implementations CVPR 2015 Kwang In Kim, James Tompkin, Hanspeter Pfister, Christian Theobalt

The iterated graph Laplacian enables high-order regularization, but it has a high computational complexity and so cannot be applied to large problems.

Dimensionality Reduction Vocal Bursts Intensity Prediction

Cannot find the paper you are looking for? You can Submit a new open access paper.