OPHAvatars: One-shot Photo-realistic Head Avatars
This addresses the need for efficient avatar creation in digital media, though it appears incremental by combining existing techniques like neural radiance fields and face restoration.
The authors tackled the problem of creating photo-realistic 3D head avatars from a single portrait, achieving results that outperform state-of-the-art methods in quantitative and qualitative evaluations.
We propose a method for synthesizing photo-realistic digital avatars from only one portrait as the reference. Given a portrait, our method synthesizes a coarse talking head video using driving keypoints features. And with the coarse video, our method synthesizes a coarse talking head avatar with a deforming neural radiance field. With rendered images of the coarse avatar, our method updates the low-quality images with a blind face restoration model. With updated images, we retrain the avatar for higher quality. After several iterations, our method can synthesize a photo-realistic animatable 3D neural head avatar. The motivation of our method is deformable neural radiance field can eliminate the unnatural distortion caused by the image2video method. Our method outperforms state-of-the-art methods in quantitative and qualitative studies on various subjects.