Research map / 3D vision / Face and shape
Geometry-aware Two-scale PIFu Representation for Human Reconstruction
Zheng Dong, Ke Xu, Ziheng Duan, Hujun Bao, Weiwei Xu, Rynson W. H. Lau
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 depth denoising supervision (multi-task) (ablation) | Geometry-aware two-scale PIFu · THuman2.0 test | P2S: 0.3143 -> 0.2652 | Improved |
| add Cross Attention Module instead of ASPP+ResCBAM (ablation) | Geometry-aware two-scale PIFu · THuman2.0 test | P2S: 0.2826 -> 0.2652 | Improved |
| add Geometry Aware Module (ablation) | Geometry-aware two-scale PIFu · THuman2.0 test | P2S: 0.2695 -> 0.2652 | Improved |
| add regularization loss L_reg (ablation) | Geometry-aware two-scale PIFu · THuman2.0 test | Chamfer: 0.2691 -> 0.2775 Chamfer; 0.2760 -> 0.2652 P2S | Mixed |
| joint multi-task training instead of sequential denoise-then-reconstruct (ablation) | Geometry-aware two-scale PIFu · THuman2.0 test | P2S: 0.3125 -> 0.2652 | Improved |
| joint multi-task training instead of sequential pipeline (ablation) | Geometry-aware two-scale PIFu · THuman2.0 test | refined depth L1: 0.1261 -> 0.0911 | Improved |
| add two-scale face PIFu (PIFu-Face) (ablation) | Geometry-aware two-scale PIFu · captured data (qualitative) | facial detail | Improved |
| weighted face-to-body fusion instead of simple merging (ablation) | Geometry-aware two-scale PIFu · captured data (qualitative) | stitching artifacts | Improved |
| proposed method vs best baseline RGBD-PIFu | RGBD-PIFu · THuman2.0 test | P2S: 0.3335 -> 0.2652 | Improved |
Closest papers by meaning
- Geo-PIFu: Geometry and Pixel Aligned Implicit Functions for Single-view Human Reconstruction (NeurIPS 2020 · similarity 0.88)
- MultiGO: Towards Multi-level Geometry Learning for Monocular 3D Textured Human Reconstruction (CVPR 2025 · similarity 0.87)
- DiffHuman: Probabilistic Photorealistic 3D Reconstruction of Humans (CVPR 2024 · similarity 0.86)
- PSHuman: Photorealistic Single-image 3D Human Reconstruction using Cross-Scale Multiview Diffusion and Explicit Remeshing (CVPR 2025 · similarity 0.85)
- SIFU: Side-view Conditioned Implicit Function for Real-world Usable Clothed Human Reconstruction (CVPR 2024 · similarity 0.85)
- Self-Supervised 3D Human Mesh Recovery from a Single Image with Uncertainty-Aware Learning (AAAI 2024 · similarity 0.85)
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.
