TL;DR
This paper introduces SCARF, a hybrid model combining mesh-based body representations with neural radiance fields to reconstruct, animate, and transfer clothing on 3D human avatars from monocular videos without requiring 3D supervision.
Contribution
The paper presents SCARF, a novel hybrid approach that separates body and clothing modeling, enabling high-quality reconstruction, animation, and clothing transfer from monocular videos.
Findings
SCARF achieves higher visual quality in clothing reconstruction than existing methods.
Clothing deforms naturally with body pose and shape changes.
Successful clothing transfer between different subjects' avatars.
Abstract
While recent work has shown progress on extracting clothed 3D human avatars from a single image, video, or a set of 3D scans, several limitations remain. Most methods use a holistic representation to jointly model the body and clothing, which means that the clothing and body cannot be separated for applications like virtual try-on. Other methods separately model the body and clothing, but they require training from a large set of 3D clothed human meshes obtained from 3D/4D scanners or physics simulations. Our insight is that the body and clothing have different modeling requirements. While the body is well represented by a mesh-based parametric 3D model, implicit representations and neural radiance fields are better suited to capturing the large variety in shape and appearance present in clothing. Building on this insight, we propose SCARF (Segmented Clothed Avatar Radiance Field), a…
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.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
MethodsSCARF
