In this paper we present a novel framework for unsupervised kinematic structure learning of complex articulated objects from a single-view image sequence. In contrast to prior motion information based methods, which estimate relatively simple articulations, our method can generate arbitrarily complex kinematic structures with skeletal topology by a successive iterative merge process. The iterative merge process is guided by a skeleton distance function which is generated from a novel object boundary generation method from sparse points. Our main contributions can be summarised as follows: (i) Unsupervised complex articulated kinematic structure learning by combining motion and skeleton information. (ii) Iterative fine-to-coarse merging strategy for adaptive motion segmentation and structure smoothing. (iii) Skeleton estimation from sparse feature points. (iv) A new highly articulated object dataset containing multi-stage complexity with ground truth. Our experiments show that the proposed method out-performs state-of-the-art methods both quantitatively and qualitatively.
|Title of host publication||2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)|
|Publisher||IEEE Computer Society|
|Publication status||Published - 7 Jun 2015|
|Event||2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) - Boston, Ma, United States|
Duration: 7 Jun 2015 → 12 Jun 2015
|Conference||2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)|
|Period||7/06/15 → 12/06/15|