all AI news
Template Free Reconstruction of Human-object Interaction with Procedural Interaction Generation
April 9, 2024, 4:48 a.m. | Xianghui Xie, Bharat Lal Bhatnagar, Jan Eric Lenssen, Gerard Pons-Moll
cs.CV updates on arXiv.org arxiv.org
Abstract: Reconstructing human-object interaction in 3D from a single RGB image is a challenging task and existing data driven methods do not generalize beyond the objects present in the carefully curated 3D interaction datasets. Capturing large-scale real data to learn strong interaction and 3D shape priors is very expensive due to the combinatorial nature of human-object interactions. In this paper, we propose ProciGen (Procedural interaction Generation), a method to procedurally generate datasets with both, plausible interaction …
abstract arxiv beyond cs.cv data datasets free human image learn object objects real data scale template type
More from arxiv.org / cs.CV updates on arXiv.org
Jobs in AI, ML, Big Data
Founding AI Engineer, Agents
@ Occam AI | New York
AI Engineer Intern, Agents
@ Occam AI | US
AI Research Scientist
@ Vara | Berlin, Germany and Remote
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Lead Data Engineer
@ WorkMoney | New York City, United States - Remote