Shubham Tulsiani

EditCtrl: Disentangled Local and Global Control for Real-Time Generative Video Editing CVPR 2026 E-RayZer: Self-supervised 3D Reconstruction as Spatial Visual Pre-training CVPR 2026 Flow3r: Factored Flow Prediction for Scalable Visual Geometry Learning CVPR 2026 AerialMegaDepth: Learning Aerial-Ground Reconstruction and View Synthesis CVPR 2025 DiffusionSfM: Predicting Structure and Motion via Ray Origin and Endpoint Diffusion CVPR 2025 Gen2Act: Human Video Generation in Novel Scenarios enables Generalizable Robot Manipulation CoRL 2025 LightSwitch: Multi-view Relighting with Material-guided Diffusion ICCV 2025 SceneFactor: Factored Latent 3D Diffusion for Controllable 3D Scene Generation CVPR 2025 Turbo3D: Ultra-fast Text-to-3D Generation CVPR 2025 UniPhy: Learning a Unified Constitutive Model for Inverse Physics Simulation CVPR 2025 Cameras as Rays: Pose Estimation via Ray Diffusion ICLR 2024 G-HOP: Generative Hand-Object Prior for Interaction Reconstruction and Grasp Synthesis CVPR 2024 MVD-Fusion: Single-view 3D via Depth-consistent Multi-view Generation CVPR 2024 Sparse-view Pose Estimation and Reconstruction via Analysis by Generative Synthesis NeurIPS 2024 Track2Act: Predicting Point Tracks from Internet Videos enables Generalizable Robot Manipulation ECCV 2024 UpFusion: Novel View Diffusion from Unposed Sparse View Observations ECCV 2024 Affordance Diffusion: Synthesizing Hand-Object Interactions CVPR 2023 Analogy-Forming Transformers for Few-Shot 3D Parsing ICLR 2023 Diffusion-Guided Reconstruction of Everyday Hand-Object Interaction Clips ICCV 2023 Manipulate by Seeing: Creating Manipulation Controllers from Pre-Trained Representations ICCV 2023 Mesh2Tex: Generating Mesh Textures from Image Queries ICCV 2023 SparseFusion: Distilling View-Conditioned Diffusion for 3D Reconstruction CVPR 2023 AutoSDF: Shape Priors for 3D Completion, Reconstruction and Generation CVPR 2022 Monocular Dynamic View Synthesis: A Reality Check NeurIPS 2022 Pre-Train, Self-Train, Distill: A Simple Recipe for Supersizing 3D Reconstruction CVPR 2022 RelPose: Predicting Probabilistic Relative Rotation for Single Objects in the Wild ECCV 2022 What's in Your Hands? 3D Reconstruction of Generic Objects in Hands CVPR 2022 A Differentiable Recipe for Learning Visual Non-Prehensile Planar Manipulation CoRL 2021 NeRS: Neural Reflectance Surfaces for Sparse-view 3D Reconstruction in the Wild NeurIPS 2021 No RL, No Simulation: Learning to Navigate without Navigating NeurIPS 2021 PixelTransformer: Sample Conditioned Signal Generation ICML 2021 Shelf-Supervised Mesh Prediction in the Wild CVPR 2021 Where2Act: From Pixels to Actions for Articulated 3D Objects ICCV 2021 Articulation-Aware Canonical Surface Mapping CVPR 2020 Discovering Motor Programs by Recomposing Demonstrations ICLR 2020 Intrinsic Motivation for Encouraging Synergistic Behavior ICLR 2020 See, Hear, Explore: Curiosity via Audio-Visual Association NeurIPS 2020 Use the Force, Luke! Learning to Predict Physical Forces by Simulating Effects CVPR 2020 Visual Imitation Made Easy CoRL 2020 3D-RelNet: Joint Object and Relational Network for 3D Prediction ICCV 2019 Canonical Surface Mapping via Geometric Cycle Consistency ICCV 2019 Compositional Video Prediction ICCV 2019 Object-centric Forward Modeling for Model Predictive Control CoRL 2019 Order-Aware Generative Modeling Using the 3D-Craft Dataset ICCV 2019 Factoring Shape, Pose, and Layout From the 2D Image of a 3D Scene CVPR 2018 Layer-structured 3D Scene Inference via View Synthesis ECCV 2018 Learning Category-Specific Mesh Reconstruction from Image Collections ECCV 2018 Multi-View Consistency as Supervisory Signal for Learning Shape and Pose Prediction CVPR 2018 Learning Shape Abstractions by Assembling Volumetric Primitives CVPR 2017 Multi-View Supervision for Single-View Reconstruction via Differentiable Ray Consistency CVPR 2017 Amodal Completion and Size Constancy in Natural Scenes ICCV 2015 Category-Specific Object Reconstruction From a Single Image CVPR 2015 Pose Induction for Novel Object Categories ICCV 2015 Viewpoints and Keypoints CVPR 2015 Virtual View Networks for Object Reconstruction CVPR 2015