Bridging the Gap: Studio-like Avatar Creation from a Monocular Phone Capture

TL;DR

This paper introduces a novel method to generate studio-like, photorealistic facial textures for avatars from simple monocular phone captures by leveraging StyleGAN2 and diffusion models, significantly improving detail and lighting realism.

Contribution

It proposes a new approach that uses StyleGAN2's $W^+$ space and diffusion super-resolution to produce high-quality, studio-like textures from casual phone videos, bridging the quality gap.

Findings

Produces photorealistic, uniformly lit avatars from monocular captures

Enhances facial detail accuracy with diffusion super-resolution

Achieves near-studio quality textures from casual phone videos

Abstract

Creating photorealistic avatars for individuals traditionally involves extensive capture sessions with complex and expensive studio devices like the LightStage system. While recent strides in neural representations have enabled the generation of photorealistic and animatable 3D avatars from quick phone scans, they have the capture-time lighting baked-in, lack facial details and have missing regions in areas such as the back of the ears. Thus, they lag in quality compared to studio-captured avatars. In this paper, we propose a method that bridges this gap by generating studio-like illuminated texture maps from short, monocular phone captures. We do this by parameterizing the phone texture maps using the $W^+$ space of a StyleGAN2, enabling near-perfect reconstruction. Then, we finetune a StyleGAN2 by sampling in the $W^+$ parameterized space using a very small set of studio-captured textures as an adversarial training signal. To further enhance the realism and accuracy of facial details, we super-resolve the output of the StyleGAN2 using carefully designed diffusion model that is guided by image gradients of the phone-captured texture map. Once trained, our method excels at producing studio-like facial texture maps from casual monocular smartphone videos. Demonstrating its capabilities, we showcase the generation of photorealistic, uniformly lit, complete avatars from monocular phone captures. The project page can be found at http://shahrukhathar.github.io/2024/07/22/Bridging.html