AvatarPerfect: User-Assisted 3D Gaussian Splatting Avatar Refinement with Automatic Pose Suggestion

TL;DR

AvatarPerfect is a user-assisted system for refining 3D Gaussian Splatting avatars by iterative manual editing and automatic pose suggestions, resulting in higher quality avatars than existing methods.

Contribution

It introduces a novel interactive framework combining manual editing with automatic pose suggestions for improved 3D avatar refinement from monocular videos.

Findings

Users achieved higher quality avatars with AvatarPerfect compared to existing methods.

The system effectively suggests poses that help users identify and correct artifacts.

User study demonstrates superior performance over SuperSplat.

Abstract

Creating high-quality 3D avatars using 3D Gaussian Splatting (3DGS) from a monocular video benefits virtual reality and telecommunication applications. However, existing automatic methods exhibit artifacts under novel poses due to limited information in the input video. We propose AvatarPerfect, a novel system that allows users to iteratively refine 3DGS avatars by manually editing the rendered avatar images. In each iteration, our system suggests a new body and camera pose to help users identify and correct artifacts. The edited images are then used to update the current avatar, and our system suggests the next body and camera pose for further refinement. To investigate the effectiveness of AvatarPerfect, we conducted a user study comparing our method to an existing 3DGS editor SuperSplat, which allows direct manipulation of Gaussians without automatic pose suggestions. The results indicate that our system enables users to obtain higher quality refined 3DGS avatars than the existing 3DGS editor.