HOLD: Category-agnostic 3D Reconstruction of Interacting Hands and Objects from Video
This enables scalable and generalizable modeling of human-object interactions for applications in robotics, AR/VR, and behavior analysis, representing a novel approach rather than an incremental improvement.
The paper tackles the problem of 3D reconstruction of interacting hands and objects from monocular video without relying on pre-scanned object templates or extensive 3D annotations, achieving state-of-the-art performance in both lab and in-the-wild settings.
Since humans interact with diverse objects every day, the holistic 3D capture of these interactions is important to understand and model human behaviour. However, most existing methods for hand-object reconstruction from RGB either assume pre-scanned object templates or heavily rely on limited 3D hand-object data, restricting their ability to scale and generalize to more unconstrained interaction settings. To this end, we introduce HOLD -- the first category-agnostic method that reconstructs an articulated hand and object jointly from a monocular interaction video. We develop a compositional articulated implicit model that can reconstruct disentangled 3D hand and object from 2D images. We also further incorporate hand-object constraints to improve hand-object poses and consequently the reconstruction quality. Our method does not rely on 3D hand-object annotations while outperforming fully-supervised baselines in both in-the-lab and challenging in-the-wild settings. Moreover, we qualitatively show its robustness in reconstructing from in-the-wild videos. Code: https://github.com/zc-alexfan/hold