A SFM-based sparse to dense 3D face reconstruction method robust to feature tracking errors

Chang Yang, Jiansheng Chen, Cong Xia, Jing Liu, Guangda SuICIP 2013 · OpenReview

Abstract

In this paper, we present a new sparse to dense 3D face reconstruction method using monocular video sequences. Structure from motion (SFM) is an effective method to reconstruct sparse 3D facial shape; however, its performance degrades drastically when tracking errors caused by self-occlusion or image noise exist. To address the problem, we propose a reliable point selection method to automatically evaluate the reliability of corresponding points obtained by optical flow. The gray level cooccurrence matrix (GLCM) is applied to the texture-based correlation evaluation and those points whose correlation coefficients are lower than a threshold will be removed. Benefiting from the SFM's capacity of dealing with missing data, our method is more robust to tracking point correspondence errors and accordingly achieves a lower 3D reconstruction error compared with traditional SFM methods without correlation checking.
BibTeX
@inproceedings{yang2013sfm,
  author = {Chang Yang and Jiansheng Chen and Cong Xia and Jing Liu and Guangda Su},
  title = {{A SFM-based sparse to dense 3D face reconstruction method robust to feature tracking errors}},
  booktitle = {ICIP},
  year = {2013},
  url = {https://openreview.net/forum?id=0wGOKABm6ap},
}

Loading related content...

Figure