Research map / 3D vision / Face and shape
ARCH: Animatable Reconstruction of Clothed Humans
Zeng Huang, Yuanlu Xu, Christoph Lassner, Hao Li, Tony Tung
Check your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Add SemDF to canonicalize arbitrary-pose humans before reconstruction (ablation) | ARCH · RenderPeople | P2S (cm): 1.98 -> 0.74 | Improved |
| Add SemDF to canonicalize arbitrary-pose humans before reconstruction (ablation) | ARCH · BUFF | P2S (cm): 1.74 -> 0.82 | Improved |
| Add GRaC differentiable render-and-compare refinement (ablation) | ARCH + SemDF · RenderPeople | Normal error: 0.042 -> 0.038 | Improved |
| Add GRaC differentiable render-and-compare refinement (ablation) | ARCH + SemDF · BUFF | Normal error: 0.045 -> 0.040 | Improved |
| Use RBF landmark-distance spatial features instead of absolute XYZ coordinates (ablation) | ARCH · Spatial feature ablation | Chamfer: 0.91 -> 0.85 | Improved |
| Use RBF landmark-distance spatial features instead of Euclidean L2 distances (ablation) | ARCH · Spatial feature ablation | P2S: 0.76 -> 0.74 | Improved |
| Use RBF landmark-distance spatial features instead of Euclidean L2 distances (ablation) | ARCH · Spatial feature ablation | Normal error: 0.043 -> 0.042 | Improved |
Closest papers by meaning
- ARCH++: Animation-Ready Clothed Human Reconstruction Revisited (ICCV 2021 · similarity 0.96)
- ICON: Implicit Clothed Humans Obtained From Normals (CVPR 2022 · similarity 0.91)
- CaPhy: Capturing Physical Properties for Animatable Human Avatars (ICCV 2023 · similarity 0.90)
- FRESA: Feedforward Reconstruction of Personalized Skinned Avatars from Few Images (CVPR 2025 · similarity 0.89)
- D^3-Human: Dynamic Disentangled Digital Human from Monocular Video (CVPR 2025 · similarity 0.89)
- VS: Reconstructing Clothed 3D Human from Single Image via Vertex Shift (CVPR 2024 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
