dc.contributor.advisor | Jat, P.M. | |
dc.contributor.author | Kapadiya, Ashik Kumar | |
dc.date.accessioned | 2020-09-22T05:43:38Z | |
dc.date.available | 2023-02-17T05:43:38Z | |
dc.date.issued | 2020 | |
dc.identifier.citation | Kapadiya, Ashik Kumar (2020). Avatar retargeting. Dhirubhai Ambani Institute of Information and Communication Technology. v, 9 p. (Acc.No: T00880) | |
dc.identifier.uri | http://drsr.daiict.ac.in//handle/123456789/959 | |
dc.description.abstract | Human Motion analysis has variety of applications including animation and content creation. In order to extract human motion and apply it to other character with different body structure and limb sizes, we require to have disentanglement between set of latent components for motion, view-angle and structure of a person. After receiving latent representations, we then combine motion with different skeletons and decode a retargeted temporal sequence. Finally, using video to video synthesis retargeted skeleton is transformed to retargeted video of an avatar. | |
dc.publisher | Dhirubhai Ambani Institute of Information and Communication Technology | |
dc.subject | Motion retargeting | |
dc.subject | Human pose estimation | |
dc.subject | Auto-encoder | |
dc.subject | Video to video synthesis (vid2vid) | |
dc.classification.ddc | 006.6 KAP | |
dc.title | Avatar retargeting | |
dc.type | Dissertation | |
dc.degree | M. Tech | |
dc.student.id | 201811052 | |
dc.accession.number | T00880 | |