USR: Unsupervised Separated 3D Garment and Human Reconstruction via Geometry and Semantic Consistency
Yue Shi, Yuxuan Xiong, Jingyi Chai, Bingbing Ni, Wenjun Zhang

TL;DR
This paper introduces USR, an unsupervised method for separately reconstructing 3D human bodies and garments from images, improving realism and enabling applications like virtual try-on without requiring 3D models.
Contribution
The paper presents a novel unsupervised layered reconstruction approach using a surface-aware neural radiance field and semantic-guided segmentation, eliminating the need for 3D supervision.
Findings
Outperforms state-of-the-art in geometry and appearance accuracy
Supports real-time reconstruction of unseen people
Enables clothing swapping and virtual try-on
Abstract
Dressed people reconstruction from images is a popular task with promising applications in the creative media and game industry. However, most existing methods reconstruct the human body and garments as a whole with the supervision of 3D models, which hinders the downstream interaction tasks and requires hard-to-obtain data. To address these issues, we propose an unsupervised separated 3D garments and human reconstruction model (USR), which reconstructs the human body and authentic textured clothes in layers without 3D models. More specifically, our method proposes a generalized surface-aware neural radiance field to learn the mapping between sparse multi-view images and geometries of the dressed people. Based on the full geometry, we introduce a Semantic and Confidence Guided Separation strategy (SCGS) to detect, segment, and reconstruct the clothes layer, leveraging the consistency…
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
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
Topics3D Shape Modeling and Analysis · Human Pose and Action Recognition · Generative Adversarial Networks and Image Synthesis
