Backing Off: Hierarchical Decomposition of Activity for 3D Novel Pose Recovery
BMVC(2009)
摘要
For model-based 3D human pose estimation, even simple models of the human body lead to high-dimensional state spaces. Where the class of activity is known a priori, low- dimensional activity models learned from training data make possible a thorough and efficient search for the best pose. Conversely, searching for solutions in the full state space places no restriction on the class of motion to be recovered, but is both difficult and expensive. This paper explores a potential middle ground between these approaches, using the hierarchical Gaussian process latent variable model to learn activity at differ- ent hierarchical scales within the human skeleton. We show that by training on full-body activity data then descending through the hierarchy in stages and exploring subtrees inde- pendently of one another, novel poses may be recovered. Experimental results on motion capture data and monocular video sequences demonstrate the utility of the approach, and comparisons are drawn with existing low-dimensional activity models.
更多查看译文
关键词
gaussian process,pose estimation,state space,human body,latent variable model
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要