Research map / 3D vision / Face and shape
Geo-PIFu: Geometry and Pixel Aligned Implicit Functions for Single-view Human Reconstruction
Tong He, John Collomosse, Hailin Jin, Stefano Soatto
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 |
|---|---|---|---|
| Fuse geometry-aligned 3D and pixel-aligned 2D features (ablation) | Geo-PIFu · DeepHuman test | CD: 2.604 -> 1.742 | Improved |
| Fuse geometry-aligned 3D and pixel-aligned 2D features (ablation) | Geo-PIFu · DeepHuman test | PSD: 4.026 -> 1.922 | Improved |
| Use geometry-aligned 3D features only rather than pixel-aligned 2D features only (ablation) | Geo-PIFu · DeepHuman test | PSD: 4.026 -> 2.629 | Improved |
| Use geometry-aligned 3D features only rather than pixel-aligned 2D features only (ablation) | Geo-PIFu · DeepHuman test | L2: 0.3009 -> 0.3164 | Hurt |
| Apply FC layers to geometry features before concatenating pixel features (ablation) | Geo-PIFu · DeepHuman test | CD: 1.742 -> 1.753 | No clear effect |
| Apply separate FC layers to geometry and pixel features before concatenating (ablation) | Geo-PIFu · DeepHuman test | CD: 1.742 -> 1.677 | No clear effect |
| Train geometry features with coarse occupancy and 3D-GAN losses (ablation) | Geometry-only Geo-PIFu · DeepHuman test | PSD: 2.629 -> 3.372 | Hurt |
Later papers that compared with this method
2 later accepted papers report Geo-PIFu as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.
- IntegratedPIFu: Integrated Pixel Aligned Implicit Function for Single-View Human Reconstruction (ECCV 2022 · better on 5 of 5 shared results)
- SHARP: Shape-Aware Reconstruction of People in Loose Clothing (IJCV 2022 · better on 4 of 4 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.
- DeepHuman — DeepHuman: 3D Human Reconstruction From a Single Image (ICCV 2019) · 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
- 3DFG-PIFu: 3D Feature Grids for Human Digitization from Sparse Views (ECCV 2024 · similarity 0.91)
- S-PIFu: Integrating Parametric Human Models with PIFu for Single-view Clothed Human Reconstruction (NeurIPS 2022 · similarity 0.91)
- SIFU: Side-view Conditioned Implicit Function for Real-world Usable Clothed Human Reconstruction (CVPR 2024 · similarity 0.89)
- 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)
- HISR: Hybrid Implicit Surface Representation for Photorealistic 3D Human Reconstruction (AAAI 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.
