REACTO: Reconstructing Articulated Objects from a Single Video
This work addresses the challenge of 3D reconstruction for general articulated objects from monocular video, which is incremental by improving upon existing dynamic neural radiance field methods.
The paper tackled the problem of reconstructing general articulated 3D objects from a single video by proposing Quasi-Rigid Blend Skinning, a novel deformation model that enhances part rigidity and joint flexibility, resulting in higher-fidelity reconstructions as shown on real and synthetic datasets.
In this paper, we address the challenge of reconstructing general articulated 3D objects from a single video. Existing works employing dynamic neural radiance fields have advanced the modeling of articulated objects like humans and animals from videos, but face challenges with piece-wise rigid general articulated objects due to limitations in their deformation models. To tackle this, we propose Quasi-Rigid Blend Skinning, a novel deformation model that enhances the rigidity of each part while maintaining flexible deformation of the joints. Our primary insight combines three distinct approaches: 1) an enhanced bone rigging system for improved component modeling, 2) the use of quasi-sparse skinning weights to boost part rigidity and reconstruction fidelity, and 3) the application of geodesic point assignment for precise motion and seamless deformation. Our method outperforms previous works in producing higher-fidelity 3D reconstructions of general articulated objects, as demonstrated on both real and synthetic datasets. Project page: https://chaoyuesong.github.io/REACTO.