HumanNeRF: Free-viewpoint Rendering of Moving People from Monocular Video

We introduce a free-viewpoint rendering method - HumanNeRF - that works on a given monocular video of a human performing complex body motions, e.g. a video from YouTube. Our method enables pausing the video at any frame and rendering the subject from arbitrary new camera viewpoints or even a full 36...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online) s. 16189 - 16199
Hlavní autoři: Weng, Chung-Yi, Curless, Brian, Srinivasan, Pratul P., Barron, Jonathan T., Kemelmacher-Shlizerman, Ira
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 01.06.2022
Témata:
Cameras
Computational modeling
Computer vision
Pattern recognition
Rendering (computer graphics)
Task analysis
Video on demand
Vision + graphics; 3D from multi-view and sensors; Computational photography
ISSN:1063-6919
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:We introduce a free-viewpoint rendering method - HumanNeRF - that works on a given monocular video of a human performing complex body motions, e.g. a video from YouTube. Our method enables pausing the video at any frame and rendering the subject from arbitrary new camera viewpoints or even a full 360-degree camera path for that particular frame and body pose. This task is particularly challenging, as it requires synthesizing photorealistic details of the body, as seen from various camera angles that may not exist in the input video, as well as synthesizing fine details such as cloth folds and facial appearance. Our method optimizes for a volumetric representation of the person in a canonical T-pose, in concert with a motion field that maps the estimated canonical representation to every frame of the video via backward warps. The motion field is decomposed into skeletal rigid and non-rigid motions, produced by deep networks. We show significant performance improvements over prior work, and compelling examples of free-viewpoint renderings from monocular video of moving humans in challenging uncontrolled capture scenarios.
ISSN:1063-6919
DOI:10.1109/CVPR52688.2022.01573