PFAvatar: Pose-Fusion 3D Personalized Avatar Reconstruction from Real-World Outfit-of-the-Day Photos
Dianbing Xi, Guoyuan An, Jingsen Zhu, Zhijian Liu, Yuan Liu, Ruiyuan Zhang, Jiayuan Lu, Yuchi Huo, Rui Wang

TL;DR
PFAvatar is a fast, high-fidelity method for reconstructing detailed 3D avatars from real-world outfit photos, overcoming occlusion and background challenges with a novel two-stage neural approach.
Contribution
It introduces a pose-aware diffusion model with a new loss for end-to-end 3D avatar reconstruction directly from full-body images, achieving significant speed and quality improvements.
Findings
Achieves 48x faster personalization than previous methods.
Outperforms state-of-the-art in fidelity and detail preservation.
Handles occlusions and complex backgrounds robustly.
Abstract
We propose PFAvatar (Pose-Fusion Avatar), a new method that reconstructs high-quality 3D avatars from Outfit of the Day(OOTD) photos, which exhibit diverse poses, occlusions, and complex backgrounds. Our method consists of two stages: (1) fine-tuning a pose-aware diffusion model from few-shot OOTD examples and (2) distilling a 3D avatar represented by a neural radiance field (NeRF). In the first stage, unlike previous methods that segment images into assets (e.g., garments, accessories) for 3D assembly, which is prone to inconsistency, we avoid decomposition and directly model the full-body appearance. By integrating a pre-trained ControlNet for pose estimation and a novel Condition Prior Preservation Loss (CPPL), our method enables end-to-end learning of fine details while mitigating language drift in few-shot training. Our method completes personalization in just 5 minutes, achieving…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
Taxonomy
TopicsGenerative Adversarial Networks and Image Synthesis · 3D Shape Modeling and Analysis · Face recognition and analysis
