Transcription of Motion Representations for Articulated Animation
{{id}} {{{paragraph}}}
Example: bachelor of science
Motion Representations for Articulated Animation
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. The regions correspond to semantically relevant anddistinct object parts, that are more easily detected in framesof the driving video. To force decoupling of foreground frombackground, we model non-object related global Motion withan additional affine transformation. To facilitate animationand prevent the leakage of the shape of the driving object,we disentangle shape and pose of objects in the region model1can animate a variety of objects, surpassing pre-vious methods by a large margin on existing benchmarks.
Recently Menapace et al. [21] introduce playable video gen-eration, where action could be selected at each timestamp. A further group of works re-target animation from a driving video to a source frame. X2Face [42] builds a canonical rep-resentation of an input face, and generates a warp field con-ditioned on the driving video.
Loading..
Tags:
Information
Domain:
Source:
Link to this page:
Please notify us if you found a problem with this document: