Research map / 3D vision / Face and shape
Function4D: Real-Time Human Volumetric Capture From Very Sparse Consumer RGBD Sensors
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 truncated PSDF features to the depth-only GeoNet (ablation) | GeoNet · Testing dataset (116 scans) | P2S × 10^-3: 2.264 -> 1.678 | Helped |
| add truncated PSDF features to the depth-only GeoNet (ablation) | GeoNet · Testing dataset (116 scans) | Chamfer × 10^-3: 2.359 -> 1.719 | Helped |
| add truncated PSDF features to the depth-only GeoNet (ablation) | GeoNet · Testing dataset (116 scans) | Normal-Consis: 0.918 -> 0.941 | Helped |
| add truncated PSDF features to the RGBD GeoNet (ablation) | GeoNet · Testing dataset (116 scans) | P2S × 10^-3: 2.36 -> 1.678 | Helped |
| add truncated PSDF features to the RGBD GeoNet (ablation) | GeoNet · Testing dataset (116 scans) | Chamfer × 10^-3: 2.458 -> 1.719 | Helped |
| add truncated PSDF features to the RGBD GeoNet (ablation) | GeoNet · Testing dataset (116 scans) | Normal-Consis: 0.916 -> 0.941 | Helped |
| use dynamic sliding fusion before implicit reconstruction (ablation) | Function4D · challenging multi-view depth observations | reconstruction noise and completeness | Helped |
| use multi-view self-attention instead of simple average-based feature aggregation (ablation) | ColorNet · color inference, especially observation boundaries | texture sharpness and plausibility | Helped |
Closest papers by meaning
- NeuralHOFusion: Neural Volumetric Rendering Under Human-Object Interactions (CVPR 2022 · similarity 0.89)
- POSEFusion: Pose-Guided Selective Fusion for Single-View Human Volumetric Capture (CVPR 2021 · similarity 0.88)
- Real-time Free-view Human Rendering from Sparse-view RGB Videos using Double Unprojected Textures (CVPR 2025 · similarity 0.85)
- Sensing Surface Patches in Volume Rendering for Inferring Signed Distance Functions (AAAI 2025 · similarity 0.84)
- ODHSR: Online Dense 3D Reconstruction of Humans and Scenes from Monocular Videos (CVPR 2025 · similarity 0.83)
- Link to the Past: Temporal Propagation for Fast 3D Human Reconstruction from Monocular Video (CVPR 2025 · similarity 0.83)
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.