A Benchmark and Evaluation of Non-Rigid Structure from Motion

TL;DR

This paper introduces a new large-scale dataset and a comprehensive benchmark for non-rigid structure from motion, facilitating progress in this challenging area of computer vision by enabling standardized evaluation of methods.

Contribution

It provides a publicly available, significantly larger dataset and a detailed benchmark for evaluating 18 NRSfM methods, advancing research in dynamic scene 3D reconstruction.

Findings

Benchmark reveals strengths and weaknesses of current methods

Identifies promising directions for future research

Provides a standardized evaluation protocol

Abstract

Non-Rigid structure from motion (NRSfM), is a long standing and central problem in computer vision and its solution is necessary for obtaining 3D information from multiple images when the scene is dynamic. A main issue regarding the further development of this important computer vision topic, is the lack of high quality data sets. We here address this issue by presenting a data set created for this purpose, which is made publicly available, and considerably larger than the previous state of the art. To validate the applicability of this data set, and provide an investigation into the state of the art of NRSfM, including potential directions forward, we here present a benchmark and a scrupulous evaluation using this data set. This benchmark evaluates 18 different methods with available code that reasonably spans the state of the art in sparse NRSfM. This new public data set and evaluation protocol will provide benchmark tools for further development in this challenging field.