Picture for Rishabh Dabral

Rishabh Dabral

Ego4o: Egocentric Human Motion Capture and Understanding from Multi-Modal Input

Add code
Apr 11, 2025
Viaarxiv icon

FRAME: Floor-aligned Representation for Avatar Motion from Egocentric Video

Add code
Mar 29, 2025
Viaarxiv icon

3HANDS Dataset: Learning from Humans for Generating Naturalistic Handovers with Supernumerary Robotic Limbs

Add code
Mar 06, 2025
Viaarxiv icon

Betsu-Betsu: Multi-View Separable 3D Reconstruction of Two Interacting Objects

Add code
Feb 19, 2025
Viaarxiv icon

Real-time Free-view Human Rendering from Sparse-view RGB Videos using Double Unprojected Textures

Add code
Dec 17, 2024
Figure 1 for Real-time Free-view Human Rendering from Sparse-view RGB Videos using Double Unprojected Textures
Figure 2 for Real-time Free-view Human Rendering from Sparse-view RGB Videos using Double Unprojected Textures
Figure 3 for Real-time Free-view Human Rendering from Sparse-view RGB Videos using Double Unprojected Textures
Figure 4 for Real-time Free-view Human Rendering from Sparse-view RGB Videos using Double Unprojected Textures
Viaarxiv icon

Retrieving Semantics from the Deep: an RAG Solution for Gesture Synthesis

Add code
Dec 09, 2024
Figure 1 for Retrieving Semantics from the Deep: an RAG Solution for Gesture Synthesis
Figure 2 for Retrieving Semantics from the Deep: an RAG Solution for Gesture Synthesis
Figure 3 for Retrieving Semantics from the Deep: an RAG Solution for Gesture Synthesis
Figure 4 for Retrieving Semantics from the Deep: an RAG Solution for Gesture Synthesis
Viaarxiv icon

BimArt: A Unified Approach for the Synthesis of 3D Bimanual Interaction with Articulated Objects

Add code
Dec 06, 2024
Figure 1 for BimArt: A Unified Approach for the Synthesis of 3D Bimanual Interaction with Articulated Objects
Figure 2 for BimArt: A Unified Approach for the Synthesis of 3D Bimanual Interaction with Articulated Objects
Figure 3 for BimArt: A Unified Approach for the Synthesis of 3D Bimanual Interaction with Articulated Objects
Figure 4 for BimArt: A Unified Approach for the Synthesis of 3D Bimanual Interaction with Articulated Objects
Viaarxiv icon

PocoLoco: A Point Cloud Diffusion Model of Human Shape in Loose Clothing

Add code
Nov 06, 2024
Figure 1 for PocoLoco: A Point Cloud Diffusion Model of Human Shape in Loose Clothing
Figure 2 for PocoLoco: A Point Cloud Diffusion Model of Human Shape in Loose Clothing
Figure 3 for PocoLoco: A Point Cloud Diffusion Model of Human Shape in Loose Clothing
Figure 4 for PocoLoco: A Point Cloud Diffusion Model of Human Shape in Loose Clothing
Viaarxiv icon

MetaCap: Meta-learning Priors from Multi-View Imagery for Sparse-view Human Performance Capture and Rendering

Add code
Mar 27, 2024
Viaarxiv icon

ConvoFusion: Multi-Modal Conversational Diffusion for Co-Speech Gesture Synthesis

Add code
Mar 26, 2024
Viaarxiv icon