Research map / 3D vision / Face and shape
High-Fidelity Human Avatars From a Single RGB Camera
Hao Zhao, Jinsong Zhang, Yu-Kun Lai, Zerong Zheng, Yingdi Xie, Yebin Liu, Kun Li
Check 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 |
|---|---|---|---|
| Use the coarse-to-fine avatar framework | Avatar reconstruction · People-Snapshot | FID: 27.7767 -> 26.4135 | Improved |
| Use the coarse-to-fine avatar framework | Avatar reconstruction · SelfieVideo | FID: 16.3087 -> 15.1284 | Improved |
| Use the dynamic surface network and proposed reconstruction method | Avatar geometry reconstruction · Scanned human models | MVE (cm): 4.5244 -> 4.4547 | Improved |
| Use the proposed method for novel view synthesis | Novel view synthesis · SelfieVideo, 20 videos | FID: 45.1285 -> 28.1964 | Improved |
| Replace input-image supervision with neural-rendering supervision (ablation) | Texture refinement · SelfieVideo | FID: 33.2064 -> 23.4513 | Improved |
| Add unsharp masking to neural-rendering supervision (ablation) | Texture refinement · SelfieVideo | FID: 23.4513 -> 15.1284 | Improved |
| Add the reference branch (ablation) | Neural rendering network · Texture detail and patterns | texture detail | Improved |
| Use the proposed training scheme (ablation) | Neural rendering network · Rendered image quality | visual quality | Improved |
| Replace static offsets with pose-dependent dynamic offsets (ablation) | Dynamic surface reconstruction · Human geometry | geometric detail | 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.
- Neural Body — Neural Body: Implicit Neural Representations With Structured Latent Codes for Novel View Synthesis of Dynamic Humans (CVPR 2021) · better on 1 of 1 shared result
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
- Pose Modulated Avatars from Video (ICLR 2024 · similarity 0.90)
- FRESA: Feedforward Reconstruction of Personalized Skinned Avatars from Few Images (CVPR 2025 · similarity 0.88)
- Real-time High-fidelity Gaussian Human Avatars with Position-based Interpolation of Spatially Distributed MLPs (CVPR 2025 · similarity 0.88)
- RAM-Avatar: Real-time Photo-Realistic Avatar from Monocular Videos with Full-body Control (CVPR 2024 · similarity 0.88)
- 3DGS-Avatar: Animatable Avatars via Deformable 3D Gaussian Splatting (CVPR 2024 · similarity 0.88)
- Relightable and Animatable Neural Avatars from Videos (AAAI 2024 · similarity 0.88)
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.
