Get 3D head that is photorealistic and animatable from 1 minute of monocular video with MonoAvatar
Get 3D head that is photorealistic and animatable from 1 minute of monocular video with MonoAvatar
Learning Personalized High Quality Volumetric Head Avatars from Monocular RGB Videos
arXiv paper abstract https://arxiv.org/abs/2304.01436
arXiv PDF paper https://arxiv.org/pdf/2304.01436.pdf
Project page https://augmentedperception.github.io/monoavatar
... propose a method to learn a high-quality implicit 3D head avatar from a monocular RGB video captured in the wild.
The learnt avatar is driven by a parametric face model to achieve user-controlled facial expressions and head poses.
... hybrid pipeline combines the geometry prior and dynamic tracking of a 3DMM with a neural radiance field to achieve fine-grained control and photorealism.
To reduce over-smoothing and improve out-of-model expressions synthesis, ... propose to predict local features anchored on the 3DMM geometry.
These learnt features are driven by 3DMM deformation and interpolated in 3D space to yield the volumetric radiance at a designated query point.
... show ... reconstruct high-quality avatars, with more accurate expression-dependent details, good generalization to out-of-training expressions, and ... superior renderings compared to other state-of-the-art ...
Please like and share this post if you enjoyed it using the buttons at the bottom!
Stay up to date. Subscribe to my posts https://morrislee1234.wixsite.com/website/contact
Web site with my other posts by category https://morrislee1234.wixsite.com/website
Comments