Research map / 3D vision / Face and shape
Free-Viewpoint RGB-D Human Performance Capture and Rendering
Phong Nguyen-Ha, Nikolaos Sarafianos, Christoph Lassner, Janne Heikkilä, Tony Tung
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 sphere-based representation with learned radius (ablation) | HVS-Net · RenderPeople test | LPIPS: 0.22 -> 0.15 | Improved |
| add sphere-based representation (ablation) | HVS-Net · RenderPeople test | PSNR: 26.15 -> 28.54 | Improved |
| add FFC global context inpainting (ablation) | HVS-Net · RenderPeople test | PSNR: 26.82 -> 28.54 | Improved |
| add Enhancer module (ablation) | HVS-Net · RenderPeople test | PSNR: 27.92 -> 28.54 | Improved |
| add Enhancer module (ablation) | HVS-Net · RenderPeople test | SSIM: 0.967 -> 0.986 | Improved |
| add Enhancer module (ablation) | HVS-Net · Real 3dMD Data | LPIPS: 0.20 -> 0.20 | Improved |
| add Enhancer module (ablation) | HVS-Net · RenderPeople (animated) | PSNR: 26.24 -> 27.45 | Improved |
| use dense instead of sparse input depth | HVS-Net · RenderPeople (static) | LPIPS: 0.15 -> 0.14 | No clear effect |
| use 100% instead of 5% input depth | HVS-Net · RenderPeople test | PSNR: 28.27 -> 28.56 | Improved |
| use 25% instead of 100% input depth | HVS-Net · RenderPeople test | PSNR: 28.56 -> 28.55 | No clear effect |
| use 5% instead of 100% input depth | HVS-Net · RenderPeople test | fps: 20 -> 25 | Improved |
| use sparse-depth HVS-Net versus SynSin with same sparse depth | HVS-Net · RenderPeople (static) | LPIPS: 0.52 -> 0.15 | 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.
- SynSin — SynSin: End-to-End View Synthesis From a Single Image (CVPR 2020) · 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
- Real-time Free-view Human Rendering from Sparse-view RGB Videos using Double Unprojected Textures (CVPR 2025 · similarity 0.88)
- Holoported Characters: Real-time Free-viewpoint Rendering of Humans from Sparse RGB Cameras (CVPR 2024 · similarity 0.88)
- High-Fidelity 3D Head Avatars Reconstruction through Spatially-Varying Expression Conditioned Neural Radiance Field (AAAI 2024 · similarity 0.87)
- Vid2Avatar-Pro: Authentic Avatar from Videos in the Wild via Universal Prior (CVPR 2025 · similarity 0.87)
- Expressive Gaussian Human Avatars from Monocular RGB Video (NeurIPS 2024 · similarity 0.87)
- Arc2Avatar: Generating Expressive 3D Avatars from a Single Image via ID Guidance (CVPR 2025 · 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.
