HumanNeRF: Free-viewpoint Rendering of Moving People from Monocular Video
University of Washington · Google (United States)
Abstract
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…
Citation impact
- FWCI
- 23.25
- Percentile
- 100%
- References
- 100
Authors
5Topics & keywords
- Computer vision
- Artificial intelligence
- Computer science
- Rendering (computer graphics)
- Computer graphics (images)
- Monocular
- Peace, Justice and strong institutions