Research map / 3D vision / Face and shape
Towards Explicit Exoskeleton for the Reconstruction of Complicated 3D Human Avatars
Yifan Zhan, Qingtian Zhu, Muyao Niu, Mingze Ma, Jiancheng Zhao, Zhihang Zhong, Xiao Sun, Yu Qiao, Yinqiang Zheng
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 adaptive joint growth (ablation) | ToMiE · DNA-Rendering | PSNR (full): 30.99 -> 31.28 | Improved |
| add adaptive joint growth (ablation) | ToMiE · DNA-Rendering (masked regions) | PSNR (masked): 19.21 -> 19.75 | Improved |
| add non-rigid deformation network for gaussian rotation and scale (ablation) | ToMiE · DNA-Rendering | PSNR (full): 30.78 -> 31.28 | Improved |
| add non-rigid deformation network (ablation) | ToMiE · DNA-Rendering | LPIPS: 0.0363 -> 0.0374 | Hurt |
| combine motion kernel with LBS weights instead of motion kernel only (ablation) | ToMiE · DNA-Rendering | PSNR (full): 30.27 -> 31.28 | Improved |
| combine LBS weights with motion kernel instead of LBS only (ablation) | ToMiE · DNA-Rendering | PSNR (masked): 18.52 -> 19.75 | Improved |
| extend SMPL skeleton with grown joints versus GauHuman baseline | 3DGS human avatar · DNA-Rendering (masked regions) | PSNR (masked): 18.26 -> 19.75 | Improved |
| use ToMiE on tight-clothing data where growth is not needed | ToMiE · ZJU-MoCap | PSNR (full): 30.91 -> 31.10 | Mixed |
| use rendering-only Im4D instead of SMPL-constrained methods | DNA-Rendering · DNA-Rendering | LPIPS: 0.0374 -> 0.0308 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 on most shared results.
- GauHuman — GauHuman: Articulated Gaussian Splatting from Monocular Human Videos (CVPR 2024) · better on 5 of 5 shared results
- 3DGS-Avatar — 3DGS-Avatar: Animatable Avatars via Deformable 3D Gaussian Splatting (CVPR 2024) · better on 2 of 3 shared results
- GART — GART: Gaussian Articulated Template Models (CVPR 2024) · better on 2 of 2 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
- REACTO: Reconstructing Articulated Objects from a Single Video (CVPR 2024 · similarity 0.85)
- MPMAvatar: Learning 3D Gaussian Avatars with Accurate and Robust Physics-Based Dynamics (NeurIPS 2025 · similarity 0.85)
- DLCA-Recon: Dynamic Loose Clothing Avatar Reconstruction from Monocular Videos (AAAI 2024 · similarity 0.85)
- SplattingAvatar: Realistic Real-Time Human Avatars with Mesh-Embedded Gaussian Splatting (CVPR 2024 · similarity 0.84)
- HumanRig: Learning Automatic Rigging for Humanoid Character in a Large Scale Dataset (CVPR 2025 · similarity 0.84)
- Reconstructing Humans with a Biomechanically Accurate Skeleton (CVPR 2025 · similarity 0.84)
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.
