Shubham Tulsiani

papers

2,182

total citations

papers (27)

RelPose: Predicting Probabilistic Relative Rotation for Single Objects in the Wild

ECCV 2022arXiv

108

citations

Articulation-Aware Canonical Surface Mapping

CVPR 2020arXiv

105

citations

Affordance Diffusion: Synthesizing Hand-Object Interactions

CVPR 2023arXiv

104

citations

No RL, No Simulation: Learning to Navigate without Navigating

NEURIPS 2021arXiv

citations

Shelf-Supervised Mesh Prediction in the Wild

CVPR 2021arXiv

citations

Track2Act: Predicting Point Tracks from Internet Videos enables Generalizable Robot Manipulation

ECCV 2024arXiv

citations

Diffusion-Guided Reconstruction of Everyday Hand-Object Interaction Clips

ICCV 2023arXiv

citations

See, Hear, Explore: Curiosity via Audio-Visual Association

NEURIPS 2020arXiv

citations

Use the Force, Luke! Learning to Predict Physical Forces by Simulating Effects

CVPR 2020arXiv

citations

MVD-Fusion: Single-view 3D via Depth-consistent Multi-view Generation

CVPR 2024arXiv

citations

Pre-Train, Self-Train, Distill: A Simple Recipe for Supersizing 3D Reconstruction

CVPR 2022arXiv

citations

G-HOP: Generative Hand-Object Prior for Interaction Reconstruction and Grasp Synthesis

CVPR 2024arXiv

citations

Mesh2Tex: Generating Mesh Textures from Image Queries

ICCV 2023arXiv

citations

Manipulate by Seeing: Creating Manipulation Controllers from Pre-Trained Representations

ICCV 2023arXiv

citations

SceneFactor: Factored Latent 3D Diffusion for Controllable 3D Scene Generation

CVPR 2025arXiv

citations

AerialMegaDepth: Learning Aerial-Ground Reconstruction and View Synthesis

CVPR 2025arXiv

citations

UpFusion: Novel View Diffusion from Unposed Sparse View Observations

ECCV 2024arXiv

citations

DiffusionSfM: Predicting Structure and Motion via Ray Origin and Endpoint Diffusion

CVPR 2025arXiv

citations

Turbo3D: Ultra-fast Text-to-3D Generation

CVPR 2025arXiv

citations

LightSwitch: Multi-view Relighting with Material-guided Diffusion

ICCV 2025arXiv

citations

UniPhy: Learning a Unified Constitutive Model for Inverse Physics Simulation

CVPR 2025arXiv

citations

Shubham Tulsiani

papers (27)

AutoSDF: Shape Priors for 3D Completion, Reconstruction and Generation

SparseFusion: Distilling View-Conditioned Diffusion for 3D Reconstruction

Where2Act: From Pixels to Actions for Articulated 3D Objects

Monocular Dynamic View Synthesis: A Reality Check

NeRS: Neural Reflectance Surfaces for Sparse-view 3D Reconstruction in the Wild

What's in Your Hands? 3D Reconstruction of Generic Objects in Hands

RelPose: Predicting Probabilistic Relative Rotation for Single Objects in the Wild

Articulation-Aware Canonical Surface Mapping

Affordance Diffusion: Synthesizing Hand-Object Interactions

No RL, No Simulation: Learning to Navigate without Navigating

Shelf-Supervised Mesh Prediction in the Wild

Track2Act: Predicting Point Tracks from Internet Videos enables Generalizable Robot Manipulation

Diffusion-Guided Reconstruction of Everyday Hand-Object Interaction Clips

See, Hear, Explore: Curiosity via Audio-Visual Association

Use the Force, Luke! Learning to Predict Physical Forces by Simulating Effects

MVD-Fusion: Single-view 3D via Depth-consistent Multi-view Generation

Pre-Train, Self-Train, Distill: A Simple Recipe for Supersizing 3D Reconstruction

G-HOP: Generative Hand-Object Prior for Interaction Reconstruction and Grasp Synthesis

Mesh2Tex: Generating Mesh Textures from Image Queries

Manipulate by Seeing: Creating Manipulation Controllers from Pre-Trained Representations

SceneFactor: Factored Latent 3D Diffusion for Controllable 3D Scene Generation

AerialMegaDepth: Learning Aerial-Ground Reconstruction and View Synthesis

UpFusion: Novel View Diffusion from Unposed Sparse View Observations

DiffusionSfM: Predicting Structure and Motion via Ray Origin and Endpoint Diffusion

Turbo3D: Ultra-fast Text-to-3D Generation

LightSwitch: Multi-view Relighting with Material-guided Diffusion

UniPhy: Learning a Unified Constitutive Model for Inverse Physics Simulation

papers (27)

AutoSDF: Shape Priors for 3D Completion, Reconstruction and Generation

SparseFusion: Distilling View-Conditioned Diffusion for 3D Reconstruction

Where2Act: From Pixels to Actions for Articulated 3D Objects

Monocular Dynamic View Synthesis: A Reality Check

NeRS: Neural Reflectance Surfaces for Sparse-view 3D Reconstruction in the Wild

What's in Your Hands? 3D Reconstruction of Generic Objects in Hands

RelPose: Predicting Probabilistic Relative Rotation for Single Objects in the Wild

Articulation-Aware Canonical Surface Mapping

Affordance Diffusion: Synthesizing Hand-Object Interactions

No RL, No Simulation: Learning to Navigate without Navigating

Shelf-Supervised Mesh Prediction in the Wild

Track2Act: Predicting Point Tracks from Internet Videos enables Generalizable Robot Manipulation

Diffusion-Guided Reconstruction of Everyday Hand-Object Interaction Clips

See, Hear, Explore: Curiosity via Audio-Visual Association

Use the Force, Luke! Learning to Predict Physical Forces by Simulating Effects

MVD-Fusion: Single-view 3D via Depth-consistent Multi-view Generation

Pre-Train, Self-Train, Distill: A Simple Recipe for Supersizing 3D Reconstruction

G-HOP: Generative Hand-Object Prior for Interaction Reconstruction and Grasp Synthesis

Mesh2Tex: Generating Mesh Textures from Image Queries

Manipulate by Seeing: Creating Manipulation Controllers from Pre-Trained Representations

SceneFactor: Factored Latent 3D Diffusion for Controllable 3D Scene Generation

AerialMegaDepth: Learning Aerial-Ground Reconstruction and View Synthesis

UpFusion: Novel View Diffusion from Unposed Sparse View Observations

DiffusionSfM: Predicting Structure and Motion via Ray Origin and Endpoint Diffusion

Turbo3D: Ultra-fast Text-to-3D Generation

LightSwitch: Multi-view Relighting with Material-guided Diffusion

UniPhy: Learning a Unified Constitutive Model for Inverse Physics Simulation