Abstract | ||
---|---|---|
•We propose a new CRF model with a novel 2D–3D pose consistency prior for 3D human pose estimation.•We propose a simple but powerful 2D-to-3D pose lifting method based on MLP.•We show the solution of the proposed CRF model can be efficiently found by the N-best strategy.•Thorough experiments show that the proposed method achieves state-of-the-art 3D human pose estimation performance. |
Year | DOI | Venue |
---|---|---|
2018 | 10.1016/j.cviu.2018.02.004 | Computer Vision and Image Understanding |
Keywords | DocType | Volume |
Human pose estimation,Conditional random fields,Deep learning | Journal | 169 |
Issue | ISSN | Citations |
1 | 1077-3142 | 1 |
PageRank | References | Authors |
0.35 | 44 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Ju Yong Chang | 1 | 105 | 9.64 |
Kyoung Mu Lee | 2 | 3228 | 153.84 |