PulseAugur
EN
LIVE 18:16:48

New frameworks reconstruct 3D objects from hand interaction videos

By PulseAugur Editorial · [3 sources] ·

Two new research papers introduce novel frameworks for reconstructing 3D objects from egocentric videos, focusing on hand interactions. The first, ROHIT, uses a Constrained Optimisation and Propagation (COP) framework to model object poses during stable grasps. The second, AGILE, employs an agentic generation approach guided by a Vision-Language Model to create watertight meshes, bypassing traditional Structure-from-Motion methods. AI

IMPACT These methods could improve digital twins for robotics and VR by enabling more accurate 3D object reconstruction from real-world interactions.

RANK_REASON Two academic papers published on arXiv presenting new methods for 3D object reconstruction.

Read on arXiv cs.CV →

AI-generated summary · Google Gemini · from 3 sources. How we write summaries →

New frameworks reconstruct 3D objects from hand interaction videos

COVERAGE [3]

  1. arXiv cs.CV TIER_1 English(EN) · Dingbang Huang, Etienne Vouga, Qixing Huang, Georgios Pavlakos ·

    Recovering Physically Plausible Human-Object Interactions from Monocular Videos

    arXiv:2606.05359v1 Announce Type: new Abstract: In this paper, we propose RePHO, a method to reconstruct physically plausible human-object interactions (HOI) from monocular videos. While existing kinematic-based approaches produce visually plausible motion, they often result in p…

  2. arXiv cs.CV TIER_1 English(EN) · Zhifan Zhu, Siddhant Bansal, Shashank Tripathi, Dima Damen ·

    Reconstructing Objects along Hand Interaction Timelines in Egocentric Video

    arXiv:2512.07394v2 Announce Type: replace Abstract: We introduce the task of Reconstructing Objects along Hand Interaction Timelines (ROHIT). We first define the Hand Interaction Timeline (HIT) from a rigid object's perspective. In a HIT, an object is first static relative to the…

  3. arXiv cs.CV TIER_1 English(EN) · Jin-Chuan Shi, Binhong Ye, Tao Liu, Junzhe He, Yangjinhui Xu, Xiaoyang Liu, Zeju Li, Hao Chen, Chunhua Shen ·

    AGILE: Hand-Object Interaction Reconstruction from Video via Agentic Generation

    arXiv:2602.04672v4 Announce Type: replace Abstract: Reconstructing dynamic hand-object interactions from monocular videos is critical for dexterous manipulation data collection and creating realistic digital twins for robotics and VR. However, current methods face two prohibitive…

RELATED ENTITIES

RELATED TOPICS