Free-Moving Object Reconstruction and Pose Estimation with Virtual Camera

TL;DR

This paper introduces a novel method for reconstructing and estimating the pose of free-moving objects from monocular RGB videos without prior assumptions, using a virtual camera system to optimize shape and pose globally.

Contribution

The method enables free interaction with objects in front of a moving camera without prior knowledge, utilizing a virtual camera to improve optimization efficiency.

Findings

Outperforms most existing methods on standard datasets.

Achieves comparable results to prior-based techniques.

Effectively reconstructs object shape and pose in egocentric videos.

Abstract

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.