Research map / 3D vision / Face and shape
SeSDF: Self-Evolved Signed Distance Field for Implicit 3D Clothed Human Reconstruction
Yukang Cao, Kai Han, Kwan-Yee K. Wong
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 the self-evolved SDF module (ablation) | SeSDF single-view reconstruction · THuman2.0 and CAPE | Chamfer Distance: 1.245 -> 1.027; 1.473 -> 1.303 | Improved |
| Add the self-evolved SDF module (ablation) | SeSDF single-view reconstruction · THuman2.0 and CAPE | P2S: 1.200 -> 0.971; 1.390 -> 1.219 | Improved |
| Add distance encoding (ablation) | SeSDF single-view reconstruction · THuman2.0 and CAPE | Chamfer Distance: 1.099 -> 1.027; 1.377 -> 1.303 | Improved |
| Add distance encoding (ablation) | SeSDF single-view reconstruction · THuman2.0 and CAPE | P2S: 1.034 -> 0.971; 1.261 -> 1.219 | Improved |
| Add the self-evolved SDF module (ablation) | SeSDF multi-view reconstruction · THuman2.0 and CAPE | Chamfer Distance: 0.802 -> 0.791; 0.854 -> 0.841 | Improved |
| Add distance encoding (ablation) | SeSDF multi-view reconstruction · THuman2.0 and CAPE | Chamfer Distance: 0.795 -> 0.791; 0.849 -> 0.841 | Improved |
| Use occlusion-aware depth fusion instead of attention fusion (ablation) | SeSDF multi-view reconstruction · THuman2.0 and CAPE | Chamfer Distance: 0.794 -> 0.791; 0.845 -> 0.841 | Improved |
| Use occlusion-aware depth fusion instead of SMPL-X visibility fusion (ablation) | SeSDF multi-view reconstruction · THuman2.0 and CAPE | Chamfer Distance: 0.841 -> 0.791; 0.925 -> 0.841 | Improved |
| Use occlusion-aware depth fusion instead of normal-based fusion (ablation) | SeSDF multi-view reconstruction · THuman2.0 and CAPE | Chamfer Distance: 0.801 -> 0.791; 0.850 -> 0.841 | Improved |
| Use occupancy prediction rather than directly extracting the evolved SDF (ablation) | SeSDF reconstruction · 3D clothed human reconstruction | surface smoothness | Improved |
| Add normal information to occupancy prediction (ablation) | SeSDF reconstruction · 3D clothed human reconstruction | occupancy prediction | Improved |
| Use 3D features from transformed SMPL-X models across views (ablation) | SeSDF multi-view reconstruction · uncalibrated multi-view reconstruction | reconstruction quality | Improved |
Later papers that compared with this method
1 later accepted paper reports SeSDF as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- 3DFG-PIFu: 3D Feature Grids for Human Digitization from Sparse Views (ECCV 2024 · better on 5 of 5 shared results)
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.
- ICON — ICON: Implicit Clothed Humans Obtained From Normals (CVPR 2022) · better on 4 of 4 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
- SIFU: Side-view Conditioned Implicit Function for Real-world Usable Clothed Human Reconstruction (CVPR 2024 · similarity 0.88)
- MultiGO: Towards Multi-level Geometry Learning for Monocular 3D Textured Human Reconstruction (CVPR 2025 · similarity 0.88)
- D^3-Human: Dynamic Disentangled Digital Human from Monocular Video (CVPR 2025 · similarity 0.88)
- VS: Reconstructing Clothed 3D Human from Single Image via Vertex Shift (CVPR 2024 · similarity 0.88)
- Diffusion-FOF: Single-View Clothed Human Reconstruction via Diffusion-Based Fourier Occupancy Field (CVPR 2024 · similarity 0.87)
- DeClotH: Decomposable 3D Cloth and Human Body Reconstruction from a Single Image (CVPR 2025 · 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.
