Research map / 3D vision / Face and shape
NeuralHumanFVV: Real-Time Neural Volumetric Human Performance Rendering Using RGB Cameras
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 |
|---|---|---|---|
| Use NeuralHumanFVV instead of the compared methods | Novel-view human rendering · RGB_1 | MAE: 27.6 ± 1.6 vs 43.7±1.9; 67.5±3.8; 95.1±4.8; 98.1±21.9 | Helped |
| Use NeuralHumanFVV instead of the compared methods | Novel-view human rendering · RGB_6 | MAE: 26.1 ± 1.2 vs 56.1±2.1; 66.4±2.2; 103.1±27.4; 144.8±6.6 | Helped |
| Add normal refinement to the geometry pipeline (ablation) | NeuralHumanFVV · Human geometry reconstruction | geometry detail | Helped |
| Replace neural geometry with SfS geometry (ablation) | NeuralHumanFVV · Human geometry reconstruction | geometry detail | Hurt |
| Use per-vertex texture mapping instead of neural texture blending (ablation) | NeuralHumanFVV · Novel-view texture synthesis | texture artifacts | Hurt |
| Use the offline AGI texturing scheme instead of neural texture blending (ablation) | NeuralHumanFVV · Novel-view texture synthesis | texture quality | Hurt |
| Render neural texture at low resolution (ablation) | NeuralHumanFVV · Novel-view texture synthesis | texture quality | Hurt |
| Remove boundary optimization (ablation) | NeuralHumanFVV · Novel-view texture synthesis | boundary quality | Hurt |
| Reduce the number of input cameras (ablation) | NeuralHumanFVV · Human performance reconstruction | average error | Hurt |
Closest papers by meaning
- NeuralHOFusion: Neural Volumetric Rendering Under Human-Object Interactions (CVPR 2022 · similarity 0.91)
- UV Volumes for Real-Time Rendering of Editable Free-View Human Performance (CVPR 2023 · similarity 0.89)
- Real-time Free-view Human Rendering from Sparse-view RGB Videos using Double Unprojected Textures (CVPR 2025 · similarity 0.87)
- IntrinsicAvatar: Physically Based Inverse Rendering of Dynamic Humans from Monocular Videos via Explicit Ray Tracing (CVPR 2024 · similarity 0.85)
- HybridNeRF: Efficient Neural Rendering via Adaptive Volumetric Surfaces (CVPR 2024 · similarity 0.85)
- Holoported Characters: Real-time Free-viewpoint Rendering of Humans from Sparse RGB Cameras (CVPR 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.