Research map / 3D vision / Face and shape
S-PIFu: Integrating Parametric Human Models with PIFu for Single-view Clothed Human Reconstruction
Kennard Chan, Guosheng Lin, Haiyu Zhao, Weisi Lin
Read the paperCheck 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 SMPL-X coordinates via ray-based sampling (C) (ablation) | PIFu + M · THuman2.0 | CD: 3.085 -> 1.999 | Improved |
| add SMPL-X coordinates via ray-based sampling (C) (ablation) | PIFu + M · THuman2.0 | P2S: 2.673 -> 1.626 | Improved |
| add SMPL-X coordinates via ray-based sampling (C) (ablation) | PIFu + M · BUFF | CD: 1.979 -> 2.022 | Hurt |
| add SMPL-X coordinates via ray-based sampling (C) (ablation) | PIFu + M · BUFF | P2S: 1.973 -> 1.840 | Improved |
| add blendweight-based soft parsing labels (B) (ablation) | PIFu + M · THuman2.0 | CD: 3.085 -> 2.595 | Improved |
| add blendweight-based soft parsing labels (B) (ablation) | PIFu + M · THuman2.0 | P2S: 2.673 -> 2.079 | Improved |
| add blendweight-based soft parsing labels (B) (ablation) | PIFu + M · BUFF | CD: 1.979 -> 2.050 | Hurt |
| add body part orientation from vertex normals (N) (ablation) | PIFu + M · THuman2.0 | CD: 3.085 -> 2.818 | Improved |
| add body part orientation from vertex normals (N) (ablation) | PIFu + M · BUFF | CD: 1.979 -> 2.060 | Hurt |
| add body part orientation from vertex normals (N) (ablation) | PIFu + M · BUFF | P2S: 1.973 -> 1.931 | Mixed |
| combine C, B and N (full S-PIFu) versus C only (ablation) | PIFu + M + C · BUFF | P2S: 1.840 -> 1.726 | Improved |
| combine C, B and N (full S-PIFu) versus C only (ablation) | PIFu + M + C · THuman2.0 | Normal: 1.413 -> 1.440 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- ARCH++ — ARCH++: Animation-Ready Clothed Human Reconstruction Revisited (ICCV 2021) · better on 5 of 5 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Geo-PIFu: Geometry and Pixel Aligned Implicit Functions for Single-view Human Reconstruction (NeurIPS 2020 · similarity 0.91)
- Fine Structure-Aware Sampling: A New Sampling Training Scheme for Pixel-Aligned Implicit Models in Single-View Human Reconstruction (AAAI 2024 · similarity 0.88)
- SIFU: Side-view Conditioned Implicit Function for Real-world Usable Clothed Human Reconstruction (CVPR 2024 · similarity 0.88)
- VS: Reconstructing Clothed 3D Human from Single Image via Vertex Shift (CVPR 2024 · similarity 0.87)
- MultiGO: Towards Multi-level Geometry Learning for Monocular 3D Textured Human Reconstruction (CVPR 2025 · similarity 0.87)
- HiLo: Detailed and Robust 3D Clothed Human Reconstruction with High-and Low-Frequency Information of Parametric Models (CVPR 2024 · similarity 0.87)
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.
