Learning Personalized High Quality Volumetric Head Avatars from Monocular RGB Videos

Supplementary Materials ⋅ CVPR 2023

Please see our project webpage https://augmentedperception.github.io/monoavatar/ for more results.

Results of driving the avatars by an unseen test video sequence of the subject.

Labels - Left: Input Driving Video, Center: Rendered Avatar, Right: Rendered Depth


Our learned avatar produces high-quality renderings and geometries, and can handle accessories like glasses:
Our method generates reasonable results for challenging long hairs. For more discussions, please refer to the limitation section at the end of the page.


More Results of Multi-view Rendering

Labels - From left to right: (1) Input Driving Video, (2) -15 degrees, (3) 0 degree, (4) +15 degrees


Our learned avatar captures personalized characteristics such as winkles:
Our method can also handle fluffy hairs and reproduce personalized complex expressions.


Results driven under different capturing conditions

Labels - Left: Input Driving Video, Center: Rendered Avatar, Right: Rendered Depth

After training, the learned avatar model can be driven by the same subject under different capturing conditions, such as differences in hair styles, illumination, and glasses.


Limitations when rendering long hairs

Labels - Left: Input Driving Video, Center: Rendered Avatar, Right: Rendered Depth

Our method has difficulties on handling long hairs with complex deformations, which cannot be captured by the 3DMM.