A Benchmark and Evaluation of Non-Rigid Structure from Motion

Non-Rigid structure from motion (NRSfM), is a long standing and central problem in computer vision, allowing us to obtain 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 of data set compiled for this purpose, which is made publicly available, and considerably larger than previous state of the art. To validate the applicability of this data set, and provide and 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 16 different methods with available code, which we argue reasonably spans the state of the art in NRSfM. We also hope, that the presented and public data set and evaluation, will provide benchmark tools for further development in this field.