4D-HOF: Hand-Object Flow Matching for Feed-Forward 4D Interaction Reconstruction

arXiv:2610.08782 · cs.CV, cs.AI, cs.GR · Submitted 2026-10-06 · Read on arXiv

cs.CV, cs.AI, cs.GR

Submitted: 2026-10-06

Updated: 2026-10-06

Code: https://github.com/microsoft/MoGe

Project page: https://tamu-visual-ai.github.io/4D-HOF

Terminology

• Flow Matching — 1× in this paper · explained in 8 episodes

Sources

• GHOST: Fast Category-agnostic Hand-Object Interaction Reconstruction from RGB Videos using Gaussian Splatting
• Grasp in Gaussians: Fast Monocular Reconstruction of Dynamic Hand-Object Interactions
• ForeHOI: Feed-forward 3D Object Reconstruction from Daily Hand-Object Interaction Videos
• Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
• Zero-shot Reconstruction of In-Scene Object Manipulation from Video
• Depth Anything 3: Recovering the Visual Space from Any Views
• Flow Matching for Generative Modeling
• Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow
• Let us Build Bridges: Understanding and Extending Diffusion Generative Models
• GeneOH Diffusion: Towards Generalizable Hand-Object Interaction Denoising via Denoising Diffusion
• AgentSTAR: Agentic Shape Tracking and Reconstruction from Monocular Videos
• DINOv2: Learning Robust Visual Features without Supervision
• Do as I Do: Dexterous Manipulation Data from Everyday Human Videos
• Embodied Hands: Modeling and Capturing Hands and Bodies Together
• HO-Cap: A Capture System and Dataset for 3D Reconstruction and Pose Tracking of Hand-Object Interaction
• ArtHOI: Taming Foundation Models for Monocular 4D Reconstruction of Hand-Articulated-Object Interactions
• AffordGrasp: Cross-Modal Diffusion for Affordance-Aware Grasp Synthesis
• Open-CHOIR: Open-World Contact-Aware 4D Hand-Object Interaction Reconstruction
• WHOLE: World-Grounded Hand-Object Lifted from Egocentric Videos
• Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generation

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models