2025
Locally Orderless Images for Optimization in Differentiable Rendering.
CoRR, March, 2025
ST-VLM: Kinematic Instruction Tuning for Spatio-Temporal Reasoning in Vision-Language Models.
CoRR, March, 2025
DWIM: Towards Tool-aware Visual Reasoning via Discrepancy-aware Workflow Generation & Instruct-Masking Tuning.
CoRR, March, 2025
Materialist: Physically Based Editing Using Single-Image Inverse Rendering.
CoRR, January, 2025
Tuned Contrastive Learning.
Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2025
2024
OpEnCam: Lensless Optical Encryption Camera.
IEEE Trans. Computational Imaging, 2024
Drive-1-to-3: Enriching Diffusion Priors for Novel View Synthesis of Real Vehicles.
CoRR, 2024
A Minimalist Prompt for Zero-Shot Policy Learning.
CoRR, 2024
Efficient Transformer Encoders for Mask2Former-style models.
CoRR, 2024
Progressive Token Length Scaling in Transformer Encoders for Efficient Universal Segmentation.
CoRR, 2024
Controllable Safety-Critical Closed-loop Traffic Simulation via Guided Diffusion.
CoRR, 2024
LLM-Assist: Enhancing Closed-Loop Planning with Language-Based Reasoning.
CoRR, 2024
Long-HOT: A Modular Hierarchical Approach for Long-Horizon Object Transport.
Proceedings of the IEEE International Conference on Robotics and Automation, 2024
Tell, Don't Show: Language Guidance Eases Transfer Across Domains in Images and Videos.
Proceedings of the Forty-first International Conference on Machine Learning, 2024
UDA-Bench: Revisiting Common Assumptions in Unsupervised Domain Adaptation Using a Standardized Framework.
Proceedings of the Computer Vision - ECCV 2024, 2024
SAFE-SIM: Safety-Critical Closed-Loop Traffic Simulation with Diffusion-Controllable Adversaries.
Proceedings of the Computer Vision - ECCV 2024, 2024
Taming Self-Training for Open-Vocabulary Object Detection.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024
Generating Enhanced Negatives for Training Language-Based Object Detectors.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024
TextureDreamer: Image-Guided Texture Synthesis through Geometry-Aware Diffusion.
,
,
,
,
,
,
,
,
,
,
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024
What You See is What You GAN: Rendering Every Pixel for High-Fidelity Geometry in 3D GANs.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024
LidaRF: Delving into Lidar for Neural Radiance Field on Street Scenes.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024
Improving the Efficiency-Accuracy Trade-off of DETR-Style Models in Practice.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024
AIDE: An Automatic Data Engine for Object Detection in Autonomous Driving.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024
Robust Disaster Assessment from Aerial Imagery Using Text-to-Image Synthetic Data.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024
Open-world Instance Segmentation: Top-down Learning with Bottom-up Supervision.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024
Instantaneous Perception of Moving Objects in 3D.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024
Self-Training Large Language Models for Improved Visual Program Synthesis With Visual Reinforcement.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024
2023
FLAVR: flow-free architecture for fast video frame interpolation.
Mach. Vis. Appl., September, 2023
Real-Time Radiance Fields for Single-Image Portrait View Synthesis.
ACM Trans. Graph., August, 2023
Spatiotemporally Consistent HDR Indoor Lighting Estimation.
ACM Trans. Graph., 2023
Improving Pseudo Labels for Open-Vocabulary Object Detection.
CoRR, 2023
FLAVR: Flow-Agnostic Video Representations for Fast Frame Interpolation.
Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2023
IDD-3D: Indian Driving Dataset for 3D Unstructured Road Scenes.
Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2023
Split to Learn: Gradient Split for Multi-Task Human Image Analysis.
Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2023
MCNeRF: Monte Carlo Rendering and Denoising for Real-Time NeRFs.
Proceedings of the SIGGRAPH Asia 2023 Conference Papers, 2023
Exploring Question Decomposition for Zero-Shot VQA.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023
Factorized Inverse Path Tracing for Efficient and Accurate Material-Lighting Estimation.
Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023
Domain Generalization Guided by Gradient Signal to Noise Ratio of Parameters.
Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023
A Theory of Topological Derivatives for Inverse Rendering of Geometry.
Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023
Efficient Controllable Multi-Task Architectures.
Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023
NeurOCS: Neural NOCS Supervision for Monocular 3D Object Localization.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023
GeoNet: Benchmarking Unsupervised Adaptation across Geographies.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023
Q: How to Specialize Large Vision-Language Models to Data-Scarce VQA Tasks? A: Self-Train on Unlabeled Images!
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023
2022
ALBench: A Framework for Evaluating Active Learning in Object Detection.
CoRR, 2022
Learning to Rearrange with Physics-Inspired Risk Awareness.
CoRR, 2022
Learning, Understanding and Interaction in Videos.
Proceedings of the NarSUM '22: Proceedings of the 1st Workshop on User-centric Narrative Summarization of Long Videos, 2022
Exploiting Unlabeled Data with Vision and Language Models for Object Detection.
Proceedings of the Computer Vision - ECCV 2022, 2022
Learning Phase Mask for Privacy-Preserving Passive Depth Estimation.
Proceedings of the Computer Vision - ECCV 2022, 2022
A Level Set Theory for Neural Implicit Evolution Under Explicit Flows.
Proceedings of the Computer Vision - ECCV 2022, 2022
Physically-Based Editing of Indoor Scene Lighting from a Single Image.
Proceedings of the Computer Vision - ECCV 2022, 2022
Learning Semantic Segmentation from Multiple Datasets with Label Shifts.
Proceedings of the Computer Vision - ECCV 2022, 2022
MemSAC: Memory Augmented Sample Consistency for Large Scale Domain Adaptation.
Proceedings of the Computer Vision - ECCV 2022, 2022
TRoVE: Transforming Road Scene Datasets into Photorealistic Virtual Environments.
Proceedings of the Computer Vision - ECCV 2022, 2022
Single-Stream Multi-level Alignment for Vision-Language Pretraining.
Proceedings of the Computer Vision - ECCV 2022, 2022
IRISformer: Dense Vision Transformers for Single-Image Inverse Rendering in Indoor Scenes.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022
PhotoScene: Photorealistic Material and Lighting Transfer for Indoor Scenes.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022
On Generalizing Beyond Domains in Cross-Domain Continual Learning.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022
Controllable Dynamic Multi-Task Architectures.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022
Weakly But Deeply Supervised Occlusion-Reasoned Parametric Road Layouts.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022
Learning to Learn across Diverse Data Biases in Deep Face Recognition.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022
Cluster-to-adapt: Few Shot Domain Adaptation for Semantic Segmentation across Disjoint Labels.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2022
2021
YMIR: A Rapid Data-centric Development Platform for Vision Applications.
CoRR, 2021
Weakly But Deeply Supervised Occlusion-Reasoned Parametric Layouts.
CoRR, 2021
Looking Farther in Parametric Scene Parsing with Ground and Aerial Imagery.
Proceedings of the IEEE International Conference on Robotics and Automation, 2021
Modulated Periodic Activations for Generalizable Local Functional Representations.
Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision, 2021
Learning Cross-Modal Contrastive Features for Video Domain Adaptation.
Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision, 2021
Fusing the Old with the New: Learning Relative Camera Pose with Geometry-Guided Uncertainty.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2021
Instance Level Affinity-Based Transfer for Unsupervised Domain Adaptation.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2021
Divide-and-Conquer for Lane-Aware Diverse Trajectory Prediction.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2021
OpenRooms: An Open Framework for Photorealistic Indoor Scene Datasets.
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2021
Cross-Domain Similarity Learning for Face Recognition in Unseen Domains.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2021
2020
Uncertainty-Aware Physically-Guided Proxy Tasks for Unseen Domain Face Anti-spoofing.
CoRR, 2020
Voting-based Approaches For Differentially Private Federated Learning.
CoRR, 2020
OpenRooms: An End-to-End Open Framework for Photorealistic Indoor Scene Datasets.
,
,
,
,
,
,
,
,
,
,
CoRR, 2020
Neural Mesh Flow: 3D Manifold Mesh Generationvia Diffeomorphic Flows.
CoRR, 2020
DAVID: Dual-Attentional Video Deblurring.
Proceedings of the IEEE Winter Conference on Applications of Computer Vision, 2020
Unsupervised and Semi-Supervised Domain Adaptation for Action Recognition from Drones.
Proceedings of the IEEE Winter Conference on Applications of Computer Vision, 2020
Neural Mesh Flow: 3D Manifold Mesh Generation via Diffeomorphic Flows.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020
Deep Keypoint-Based Camera Pose Estimation with Geometric Constraints.
Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems, 2020
Learning Monocular Visual Odometry via Self-Supervised Long-Term Modeling.
Proceedings of the Computer Vision - ECCV 2020, 2020
Single View Metrology in the Wild.
Proceedings of the Computer Vision - ECCV 2020, 2020
Object Detection with a Unified Label Space from Multiple Datasets.
Proceedings of the Computer Vision - ECCV 2020, 2020
Pseudo RGB-D for Self-improving Monocular SLAM and Depth Prediction.
Proceedings of the Computer Vision - ECCV 2020, 2020
Single-Shot Neural Relighting and SVBRDF Estimation.
Proceedings of the Computer Vision - ECCV 2020, 2020
Improving Face Recognition by Clustering Unlabeled Faces in the Wild.
Proceedings of the Computer Vision - ECCV 2020, 2020
Domain Adaptive Semantic Segmentation Using Weak Labels.
Proceedings of the Computer Vision - ECCV 2020, 2020
SMART: Simultaneous Multi-Agent Recurrent Trajectory Prediction.
Proceedings of the Computer Vision - ECCV 2020, 2020
Towards Universal Representation Learning for Deep Face Recognition.
Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020
Understanding Road Layout From Videos as a Whole.
Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020
Through the Looking Glass: Neural 3D Reconstruction of Transparent Shapes.
Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020
Inverse Rendering for Complex Indoor Scenes: Shape, Spatially-Varying Lighting and SVBRDF From a Single Image.
Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020
Peek-a-Boo: Occlusion Reasoning in Indoor Scenes With Plane Representations.
Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020
Private-kNN: Practical Differential Privacy for Computer Vision.
Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020
Adaptation Across Extreme Variations using Unlabeled Bridges.
Proceedings of the 31st British Machine Vision Conference 2020, 2020
Adversarial Learning of Privacy-Preserving and Task-Oriented Representations.
Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence, 2020
2019
Deep Supervision with Intermediate Concepts.
IEEE Trans. Pattern Anal. Mach. Intell., 2019
Degeneracy in Self-Calibration Revisited and a Deep Learning Solution for Uncalibrated SLAM.
CoRR, 2019
Pose-variant 3D Facial Attribute Generation.
CoRR, 2019
Adaptation Across Extreme Variations using Unlabeled Domain Bridges.
CoRR, 2019
Memory Warps for Long-Term Online Video Representations and Anticipation.
Proceedings of the IEEE Winter Conference on Applications of Computer Vision, 2019
IDD: A Dataset for Exploring Problems of Autonomous Navigation in Unconstrained Environments.
Proceedings of the IEEE Winter Conference on Applications of Computer Vision, 2019
Single-Shot Analysis of Refractive Shape Using Convolutional Neural Networks.
Proceedings of the IEEE Winter Conference on Applications of Computer Vision, 2019
Degeneracy in Self-Calibration Revisited and a Deep Learning Solution for Uncalibrated SLAM.
Proceedings of the 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2019
Unsupervised Domain Adaptation for Distance Metric Learning.
Proceedings of the 7th International Conference on Learning Representations, 2019
Proceedings of the 7th International Conference on Learning Representations, 2019
Domain Adaptation for Structured Output via Discriminative Patch Representations.
Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision, 2019
Universal Semi-Supervised Semantic Segmentation.
Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision, 2019
Learning Structure-And-Motion-Aware Rolling Shutter Correction.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2019
A Parametric Top-View Representation of Complex Road Scenes.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2019
Gotta Adapt 'Em All: Joint Pixel and Feature-Level Domain Adaptation for Recognition in the Wild.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, 2019
Active Adversarial Domain Adaptation.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, 2019
Feature Transfer Learning for Face Recognition With Under-Represented Data.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2019
2018
Learning to reconstruct shape and spatially-varying reflectance from a single image.
ACM Trans. Graph., 2018
SVBRDF-Invariant Shape and Reflectance Estimation from a Light-Field Camera.
IEEE Trans. Pattern Anal. Mach. Intell., 2018
Memory Warps for Learning Long-Term Online Video Representations.
CoRR, 2018
Feature Transfer Learning for Deep Face Recognition with Long-Tail Data.
CoRR, 2018
Joint Pixel and Feature-level Domain Adaptation in the Wild.
CoRR, 2018
Learning to See Through Turbulent Water.
Proceedings of the 2018 IEEE Winter Conference on Applications of Computer Vision, 2018
Learning to Look around Objects for Top-View Representations of Outdoor Scenes.
Proceedings of the Computer Vision - ECCV 2018, 2018
Materials for Masses: SVBRDF Acquisition with a Single Mobile Phone Image.
Proceedings of the Computer Vision - ECCV 2018, 2018
Hierarchical Metric Learning and Matching for 2D and 3D Geometric Correspondences.
Proceedings of the Computer Vision - ECCV 2018, 2018
Learning to Adapt Structured Output Space for Semantic Segmentation.
Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition, 2018
2017
Reconstruction for Feature Disentanglement in Pose-invariant Face Recognition.
CoRR, 2017
Weakly Supervised Generative Adversarial Networks for 3D Reconstruction.
CoRR, 2017
Learning Efficient Object Detection Models with Knowledge Distillation.
Proceedings of the Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, 2017
Towards Large-Pose Face Frontalization in the Wild.
Proceedings of the IEEE International Conference on Computer Vision, 2017
Unsupervised Domain Adaptation for Face Recognition in Unlabeled Videos.
Proceedings of the IEEE International Conference on Computer Vision, 2017
Reconstruction-Based Disentanglement for Pose-Invariant Face Recognition.
Proceedings of the IEEE International Conference on Computer Vision, 2017
Person Re-identification in the Wild.
Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition, 2017
Learning Random-Walk Label Propagation for Weakly-Supervised Semantic Segmentation.
Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition, 2017
Deep Network Flow for Multi-object Tracking.
Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition, 2017
Deep Supervision with Shape Concepts for Occlusion-Aware 3D Object Parsing.
Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition, 2017
Robust Energy Minimization for BRDF-Invariant Shape from Light Fields.
Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition, 2017
DESIRE: Distant Future Prediction in Dynamic Scenes with Interacting Agents.
Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition, 2017
Weakly Supervised 3D Reconstruction with Adversarial Constraint.
Proceedings of the 2017 International Conference on 3D Vision, 2017
2016
High Accuracy Monocular SFM and Scale Correction for Autonomous Driving.
IEEE Trans. Pattern Anal. Mach. Intell., 2016
The Information Available to a Moving Observer on Shape with Unknown, Isotropic BRDFs.
IEEE Trans. Pattern Anal. Mach. Intell., 2016
Person Re-identification in the Wild.
CoRR, 2016
Atomic scenes for scalable traffic scene recognition in monocular videos.
Proceedings of the 2016 IEEE Winter Conference on Applications of Computer Vision, 2016
Universal Correspondence Network.
Proceedings of the Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems 2016, 2016
Deep Deformation Network for Object Landmark Localization.
Proceedings of the Computer Vision - ECCV 2016, 2016
A 4D Light-Field Dataset and CNN Architectures for Material Recognition.
Proceedings of the Computer Vision - ECCV 2016, 2016
SVBRDF-Invariant Shape and Reflectance Estimation from Light-Field Cameras.
Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition, 2016
WarpNet: Weakly Supervised Matching for Single-View Reconstruction.
Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition, 2016
A Continuous Occlusion Model for Road Scene Understanding.
Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition, 2016
2015
Joint SFM and detection cues for monocular 3D localization in road scenes.
Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2015
2014
Computer Vision, A Reference Guide, 2014
On Shape and Material Recovery from Motion.
Proceedings of the Computer Vision - ECCV 2014, 2014
Robust Scale Estimation in Real-Time Monocular SFM for Autonomous Driving.
Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition, 2014
What Camera Motion Reveals about Shape with Unknown BRDF.
Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition, 2014
2013
On Differential Photometric Reconstruction for Unknown, Isotropic BRDFs.
IEEE Trans. Pattern Anal. Mach. Intell., 2013
Parallel, real-time monocular visual odometry.
Proceedings of the 2013 IEEE International Conference on Robotics and Automation, 2013
What Object Motion Reveals about Shape with Unknown BRDF and Lighting.
Proceedings of the 2013 IEEE Conference on Computer Vision and Pattern Recognition, 2013
Dense Object Reconstruction with Semantic Priors.
Proceedings of the 2013 IEEE Conference on Computer Vision and Pattern Recognition, 2013
2011
On the Duality of Forward and Inverse Light Transport.
IEEE Trans. Pattern Anal. Mach. Intell., 2011
What an image reveals about material reflectance.
Proceedings of the IEEE International Conference on Computer Vision, 2011
A theory of differential photometric stereo for unknown isotropic BRDFs.
Proceedings of the 24th IEEE Conference on Computer Vision and Pattern Recognition, 2011
2010
Globally Optimal Algorithms for Stratified Autocalibration.
Int. J. Comput. Vis., 2010
A Dual Theory of Inverse and Forward Light Transport.
Proceedings of the Computer Vision, 2010
2009
From pictures to 3D : global optimization for scene reconstruction.
PhD thesis, 2009
Moving in stereo: Efficient structure and motion using lines.
Proceedings of the IEEE 12th International Conference on Computer Vision, ICCV 2009, Kyoto, Japan, September 27, 2009
2008
Practical Global Optimization for Multiview Geometry.
Int. J. Comput. Vis., 2008
Globally optimal bilinear programming for computer vision applications.
Proceedings of the 2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2008), 2008
2007
High Precision Multi-touch Sensing on Surfaces using Overhead Cameras.
Proceedings of the Second IEEE International Workshop on Horizontal Interactive Human-Computer Systems (Tabletop 2007), 2007
Globally Optimal Affine and Metric Upgrades in Stratified Autocalibration.
Proceedings of the IEEE 11th International Conference on Computer Vision, 2007
Autocalibration via Rank-Constrained Estimation of the Absolute Quadric.
Proceedings of the 2007 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2007), 2007
ShadowCuts: Photometric Stereo with Shadows.
Proceedings of the 2007 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2007), 2007
2005
Reflections on the Generalized Bas-Relief Ambiguity.
Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2005), 2005
2003
Real-Time Camera Pose in a Room.
Proceedings of the Computer Vision Systems, Third International Conference, 2003