Research map / 3D vision / Face and shape
DIFu: Depth-Guided Implicit Function for Clothed Human Reconstruction
Dae-Young Song, HeeKyung Lee, Jeongil Seo, Donghyeon Cho
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 |
|---|---|---|---|
| replace the SMPL volume with projected front/back depth maps as the 3D prior | DIFu versus PaMIR · THuman2.0 | P2S: 4.071 -> 2.992 | Improved |
| replace the SMPL volume with projected front/back depth maps as the 3D prior | DIFu versus ICON · BUFF | P2S: 3.621 -> 3.375 | Improved |
| use the Ladv-trained hallucinator at inference while training with the non-adversarial hallucinator (ablation) | DIFu · THuman2.0 | P2S: 3.331 -> 2.992 | Improved |
| use the Ladv-trained hallucinator at inference while training with the non-adversarial hallucinator (ablation) | DIFu · BUFF | P2S: 3.465 -> 3.374 | Improved |
| use the Ladv-trained hallucinator during occupancy-network training (ablation) | DIFu · THuman2.0 | P2S: 2.992 -> 3.484 | Hurt |
| use the Ladv-trained hallucinator during occupancy-network training (ablation) | DIFu · BUFF | P2S: 3.374 -> 3.525 | Hurt |
| add the SMPL voxel encoder fS to the depth estimator (ablation) | DIFu · THuman2.0 | P2S: 3.214 -> 2.992 | Improved |
| add the SMPL voxel encoder fS to the depth estimator (ablation) | DIFu · THuman2.0 | Chamfer: 3.146 -> 2.952 | Improved |
| add the SMPL voxel encoder fS to the depth estimator (ablation) | DIFu · THuman2.0 | Normal: 0.124 -> 0.119 | Improved |
| add the SMPL voxel encoder fS to the depth estimator (ablation) | DIFu · THuman2.0 | MSE: 0.084 -> 0.082 | Improved |
| add the SMPL voxel encoder fS to the depth estimator (ablation) | DIFu · THuman2.0 | LPIPS: 0.126 -> 0.124 | Improved |
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 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
- SIFU: Side-view Conditioned Implicit Function for Real-world Usable Clothed Human Reconstruction (CVPR 2024 · similarity 0.91)
- HiLo: Detailed and Robust 3D Clothed Human Reconstruction with High-and Low-Frequency Information of Parametric Models (CVPR 2024 · similarity 0.88)
- MultiGO: Towards Multi-level Geometry Learning for Monocular 3D Textured Human Reconstruction (CVPR 2025 · similarity 0.87)
- D^3-Human: Dynamic Disentangled Digital Human from Monocular Video (CVPR 2025 · similarity 0.87)
- 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.
