Learning non-rigid surface reconstruction from spatio-temporal image patches
Pedone, Matteo; Mostafa, Abdelrahman; Heikkilä, Janne (2021-05-05)
M. Pedone, A. Mostafa and J. Heikkilä, "Learning non-rigid surface reconstruction from spatia-temporal image patches," 2020 25th International Conference on Pattern Recognition (ICPR), 2021, pp. 10134-10140, doi: 10.1109/ICPR48806.2021.9412352
© 2021 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
https://rightsstatements.org/vocab/InC/1.0/
https://urn.fi/URN:NBN:fi-fe2021102151933
Tiivistelmä
Abstract
We present a method to reconstruct a dense spatiotemporal depth map of a non-rigidly deformable object directly from a video sequence. The estimation of depth is performed locally on spatio-temporal patches of the video, and then the full depth video of the entire shape is recovered by combining them together. Since the geometric complexity of a local spatiotemporal patch of a deforming non-rigid object is often simple enough to be faithfully represented with a parametric model, we artificially generate a database of small deforming rectangular meshes rendered with different material properties and light conditions, along with their corresponding depth videos, and use such data to train a convolutional neural network. We tested our method on both synthetic and Kinect data and experimentally observed that the reconstruction error is significantly lower than the one obtained using conventional non-rigid structure from motion approaches.
Kokoelmat
- Avoin saatavuus [38840]