DiGS-Avatar: Single-Image Animatable 3D Human Reconstruction via UV-Space Diffusion

2026-08-21

AI Summary

为解决单图像3D人体重建中的纹理平滑和几何不一致问题，提出DiGS-Avatar方法，通过UV空间扩散模型结合教师-学生框架生成高质量可动画3D人体。

Abstract

Single-image 3D human reconstruction often suffers from over-smoothed textures and geometric inconsistencies. While diffusion models improve generative quality, their reliance on multi-view synthesis prior to 3D reconstruction is computationally expensive and prone to view inconsistency. We propose DiGS-Avatar, which reformulates this task as an efficient, diffusion-based UV-latent completion task, ensuring 3D consistency by design. To capture accurate spatial structure, we introduce a teacher-student framework where a multi-view teacher provides geometrically aligned pseudo-ground-truth latents to supervise a single-view diffusion student. Treating this inferred latent as a robust structural skeleton, our method injects high-level semantic features to accurately recover fine textural details without disrupting spatial integrity. The refined representation is then decoded into 3D Gaussian primitives. Extensive experiments demonstrate that DiGS-Avatar achieves state-of-the-art or highly competitive visual fidelity and zero-shot generalization, while reconstructing a fully animatable 3D avatar in just 0.71 seconds. Code is available at https://github.com/KLMAV-CUC/DiGS-Avatar.

Problem

• single-image 3D human reconstruction
• over-smoothed textures
• geometric inconsistencies
• diffusion models
• multi-view synthesis

Innovation

• UV-space diffusion
• teacher-student framework
• pseudo-ground-truth latents
• semantic features
• 3D Gaussian primitives