Research map / 3D vision / Face and shape
TotalSelfScan: Learning Full-body Avatars from Self-Portrait Videos of Faces, Hands, and Bodies
Junting Dong, Qi Fang, Yudong Guo, Sida Peng, Qing Shuai, Xiaowei Zhou, Hujun Bao
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 |
|---|---|---|---|
| use multi-part networks instead of a single network with the same parameter count (ablation) | TotalSelfScan · SynTotalHuman head reconstruction | P2S (cm): 1.03 -> 0.59 | Improved |
| use multi-part networks instead of a single network (ablation) | TotalSelfScan · SynTotalHuman hands reconstruction | P2S (cm): 1.25 -> 0.55 | Improved |
| use multi-part networks instead of a single network (ablation) | TotalSelfScan · SynTotalHuman total reconstruction | P2S (cm): 1.95 -> 1.84 | Improved |
| use multi-part networks instead of a single network (ablation) | TotalSelfScan · SynTotalHuman total image synthesis | PSNR: 25.19 -> 26.15 | Improved |
| use multi-part networks instead of a single network (ablation) | TotalSelfScan · SynTotalHuman head image synthesis | PSNR: 20.38 -> 22.23 | Improved |
| add non-rigid ray transformation (global view directions) (ablation) | TotalSelfScan · SynTotalHuman total image synthesis | PSNR: 25.43 -> 26.15 | Improved |
| add non-rigid ray transformation (ablation) | TotalSelfScan · SynTotalHuman head image synthesis | PSNR: 21.07 -> 22.23 | Improved |
| add non-rigid ray transformation (ablation) | TotalSelfScan · SynTotalHuman hands image synthesis | LPIPS: 0.085 -> 0.076 | Improved |
| refine head transformation with reconstructed surface alignment instead of FLAME-SMPLH registration only (ablation) | TotalSelfScan · TotalHuman head-body alignment | qualitative alignment | Improved |
| add geometry composition loss Lg (ablation) | TotalSelfScan · TotalHuman surface transition | qualitative smoothness | Improved |
| add latent code optimization and color field fusion for appearance composition (ablation) | TotalSelfScan · TotalHuman appearance consistency | qualitative consistency | Improved |
| use proposed part-specific multi-part method instead of AniSDF | TotalSelfScan vs AniSDF · SynTotalHuman head reconstruction | P2S (cm): 0.76 -> 0.59 | 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.
- NeuralBody — Neural Body: Implicit Neural Representations With Structured Latent Codes for Novel View Synthesis of Dynamic Humans (CVPR 2021) · better on 3 of 3 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
- Monocular Total Capture: Posing Face, Body, and Hands in the Wild (CVPR 2019 · similarity 0.91)
- Multi-HMR: Multi-Person Whole-Body Human Mesh Recovery in a Single Shot (ECCV 2024 · similarity 0.89)
- One-Stage 3D Whole-Body Mesh Recovery With Component Aware Transformer (CVPR 2023 · similarity 0.89)
- MUC: Mixture of Uncalibrated Cameras for Robust 3D Human Body Reconstruction (AAAI 2025 · similarity 0.87)
- AiOS: All-in-One-Stage Expressive Human Pose and Shape Estimation (CVPR 2024 · similarity 0.87)
- Human Gaussian Splatting: Real-time Rendering of Animatable Avatars (CVPR 2024 · 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.
