DC Field | Value | Language |
---|---|---|
dc.contributor.author | 도승욱 | - |
dc.date.accessioned | 2023-08-31T16:35:35Z | - |
dc.date.available | 2023-08-31T16:35:35Z | - |
dc.date.issued | 2023 | - |
dc.identifier.other | OAK-2015-10233 | - |
dc.identifier.uri | http://postech.dcollection.net/common/orgView/200000693173 | ko_KR |
dc.identifier.uri | https://oasis.postech.ac.kr/handle/2014.oak/118430 | - |
dc.description | Master | - |
dc.description.abstract | We present PointActor, a method capable of efficiently generating novel view images from an animated person in a video. PointActor first represents a T-shaped human point cloud in a canonical space and then maps it to an observation space that faithfully characterizes the geometry of the person. Human appearance is represented as a combination of a multi-level hash encoding and a shallow MLP. Contrary to other approaches that use backward mapping, we leverage forward mapping to render free-viewpoint images alongside novel human poses while effectively disentangling complex human gestures such as overlapping limbs. On top of obtaining those natural poses, we further switch from a volumetric rendering approach to a splat rendering approach which, coupled with the point cloud space representation, allows us to perform inference up to 57$\times$ faster than previous methods. | - |
dc.language | eng | - |
dc.publisher | 포항공과대학교 | - |
dc.title | PointActor: Animatable Human Radiance Field from Monocular Video | - |
dc.title.alternative | 비디오로부터 애니메이션이 가능한 사람 래디언스 필드 복원 | - |
dc.type | Thesis | - |
dc.contributor.college | 컴퓨터공학과 | - |
dc.date.degree | 2023- 8 | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.
library@postech.ac.kr Tel: 054-279-2548
Copyrights © by 2017 Pohang University of Science ad Technology All right reserved.