Transcription of Motion Representations for Articulated Animation
{{id}} {{{paragraph}}}
Motion Representations for Articulated AnimationAliaksandr Siarohin1 , Oliver J. Woodford , Jian Ren2, Menglei Chai2and Sergey Tulyakov21 DISI, University of Trento, Italy,2 Snap Inc., Santa Monica, Work done while at Snap propose novel Motion Representations for animatingarticulated objects consisting of distinct parts. In a com-pletely unsupervised manner, our method identifies objectparts, tracks them in a driving video, and infers their motionsby considering their principal axes. In contrast to the previ-ous keypoint-based works, our method extracts meaningfuland consistentregions, describing locations, shape, andpose.
Monkey-Net [31] learns a set of unsupervised keypoints to generate animations. Follow- ... being Z, and Mk(z) is the k-th heatmap weight at pixel z. Thus, the translation component of the affine transformation (which is the last column of Ak X R) can be …
Domain:
Source:
Link to this page:
Please notify us if you found a problem with this document:
{{id}} {{{paragraph}}}