A Benchmark and Evaluation of Non-Rigid Structure from Motion
This addresses a data bottleneck for researchers in computer vision working on dynamic 3D reconstruction, though it is incremental as it builds on existing NRSfM methods.
The authors tackled the lack of high-quality datasets for Non-Rigid Structure from Motion (NRSfM) by creating a publicly available dataset that is considerably larger than previous ones, and they benchmarked 18 state-of-the-art methods to evaluate the field and provide tools for future development.
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.