We propose an approach for reconstructing free-moving object from a monocular RGB video. Most existing methods either assume scene prior, hand pose prior, object category pose prior, or rely on local optimization with multiple sequence segments. We propose a method that allows free interaction with the object in front of a moving camera without relying on any prior, and optimizes the sequence globally without any segments. We progressively optimize the object shape and pose simultaneously based on an implicit neural representation. A key aspect of our method is a virtual camera system that reduces the search space of the optimization significantly. We evaluate our method on the standard HO3D dataset and a collection of egocentric RGB sequences captured with a head-mounted device. We demonstrate that our approach outperforms most methods significantly, and is on par with recent techniques that assume prior information.
@article{arxiv.2405.05858,
title = {Free-Moving Object Reconstruction and Pose Estimation with Virtual Camera},
author = {Haixin Shi and Yinlin Hu and Daniel Koguciuk and Juan-Ting Lin and Mathieu Salzmann and David Ferstl},
journal= {arXiv preprint arXiv:2405.05858},
year = {2024}
}