Research map / 3D vision / Face and shape
IntegratedPIFu: Integrated Pixel Aligned Implicit Function for Single-View Human Reconstruction
Kennard Yanting 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 High-resolution Integrator (HRI) in place of PIFuHD high-res module | PIFuHD · THuman2.0 test | P2S (1e-4): 2.540 -> 2.177 | Improved |
| add High-resolution Integrator (HRI) in place of PIFuHD high-res module | PIFuHD · THuman2.0 test | Chamfer distance (1e-4): 2.800 -> 2.841 | No clear effect |
| add depth-oriented sampling (DOS) to HRI (ablation) | IntegratedPIFu · THuman2.0 test | Chamfer distance (1e-4): 2.841 -> 2.711 | Improved |
| add depth-oriented sampling (DOS) to HRI (ablation) | IntegratedPIFu · BUFF | Normal error: 1.762 -> 1.800 | Hurt |
| add predicted depth and parsing maps to HRI+DOS (ablation) | IntegratedPIFu · THuman2.0 test | Chamfer distance (1e-4): 2.711 -> 3.040 | Hurt |
| add predicted depth map only to HRI+DOS (ablation) | IntegratedPIFu · BUFF | Chamfer distance (1e-3): 2.029 -> 2.182 | Hurt |
| add parsing map only to HRI+DOS (ablation) | IntegratedPIFu · THuman2.0 test | Normal error: 1.643 -> 1.780 | Hurt |
| add predicted depth and/or parsing maps to PIFu backbone (ablation) | PIFuHD backbone · qualitative | broken limbs and floating artefacts | Improved |
| replace spatial sampling with depth-oriented sampling (ablation) | PIFuHD · qualitative | fine details and wavy artefacts | Improved |
| replace PIFuHD high-res PIFu with HRI (ablation) | PIFuHD · qualitative | floating artefacts | 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.
- Geo-PIFu — Geo-PIFu: Geometry and Pixel Aligned Implicit Functions for Single-view Human Reconstruction (NeurIPS 2020) · 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
- Fine Structure-Aware Sampling: A New Sampling Training Scheme for Pixel-Aligned Implicit Models in Single-View Human Reconstruction (AAAI 2024 · similarity 0.90)
- 3DFG-PIFu: 3D Feature Grids for Human Digitization from Sparse Views (ECCV 2024 · similarity 0.89)
- PSHuman: Photorealistic Single-image 3D Human Reconstruction using Cross-Scale Multiview Diffusion and Explicit Remeshing (CVPR 2025 · similarity 0.86)
- SIFU: Side-view Conditioned Implicit Function for Real-world Usable Clothed Human Reconstruction (CVPR 2024 · similarity 0.86)
- BLADE: Single-view Body Mesh Estimation through Accurate Depth Estimation (CVPR 2025 · similarity 0.85)
- SiTH: Single-view Textured Human Reconstruction with Image-Conditioned Diffusion (CVPR 2024 · similarity 0.84)
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.
