Integral Human Pose Regression
| Autor: | Shuang Liang, Xiao Sun, Yichen Wei, Bin Xiao, Fangyin Wei |
|---|---|
| Rok vydání: | 2018 |
| Předmět: |
Work (thermodynamics)
Computer science business.industry Deep learning Representation (systemics) 020207 software engineering 02 engineering and technology 3D pose estimation Regression Simple (abstract algebra) 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Artificial intelligence Differentiable function business Pose Algorithm |
| Zdroj: | Computer Vision – ECCV 2018 ISBN: 9783030012304 ECCV (6) |
| DOI: | 10.1007/978-3-030-01231-1_33 |
| Popis: | State-of-the-art human pose estimation methods are based on heat map representation. In spite of the good performance, the representation has a few issues in nature, such as non-differentiable post-processing and quantization error. This work shows that a simple integral operation relates and unifies the heat map representation and joint regression, thus avoiding the above issues. It is differentiable, efficient, and compatible with any heat map based methods. Its effectiveness is convincingly validated via comprehensive ablation experiments under various settings, specifically on 3D pose estimation, for the first time. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|