Research map / 3D vision / Gaussian splatting
HandSCS: Structural Coordinate Space for Animatable Hand Gaussian Splatting
Yilan Dong, Wenqing WANG, Qing Wang, Jiahao Yang, Haohe Liu, Xiatian Zhu, Greg Slabaugh, Shanxin Yuan
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 |
|---|---|---|---|
| build virtual bones in canonical space instead of posed space (ablation) | HandSCS · InterHand2.6M test/Capture0 | LPIPS: 0.0303 -> 0.0291 (PSNR 32.87 -> 32.91) | Improved |
| add the intra-pose component (ablation) | HandSCS · InterHand2.6M test/Capture0 | PSNR: 32.42 -> 32.91 | Improved |
| add the intra-pose component (ablation) | HandSCS · InterHand2.6M test/Capture0 | LPIPS: 0.0335 -> 0.0291 | Improved |
| add interpolation parameter t to virtual bone endpoints (ablation) | HandSCS · InterHand2.6M test/Capture0 | PSNR: 32.67 -> 32.91 | Improved |
| add offset term Delta to virtual bone endpoints (ablation) | HandSCS · InterHand2.6M test/Capture0 | PSNR: 32.69 -> 32.91 | Improved |
| add offset term Delta to virtual bone endpoints (ablation) | HandSCS · InterHand2.6M test/Capture0 | LPIPS: 0.0300 -> 0.0291 | Improved |
| use HandSCS instead of strongest baseline for novel pose | HandSCS · InterHand2.6M novel pose | PSNR: +1.24 dB PSNR, +0.008 SSIM, 33.4% relative LPIPS reduction | Improved |
| use HandSCS instead of GauHuman for sparse-view NVS | HandSCS · InterHand2.6M sparse-view NVS | PSNR: +3.78 dB PSNR, +0.017 SSIM, 0.017 LPIPS reduction (37% relative) | Improved |
| compare against LiveHand on SSIM under sparse views | HandSCS · InterHand2.6M sparse-view NVS (test/Capture0) | SSIM: 0.984 -> 0.973 | Hurt |
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 8 of 8 shared results
- 3DGS-Avatar — 3DGS-Avatar: Animatable Avatars via Deformable 3D Gaussian Splatting (CVPR 2024) · better on 4 of 4 shared results
- HandAvatar — Hand Avatar: Free-Pose Hand Animation and Rendering From Monocular Video (CVPR 2023) · 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
- Learning Interaction-aware 3D Gaussian Splatting for One-shot Hand Avatars (NeurIPS 2024 · similarity 0.91)
- Human Gaussian Splatting: Real-time Rendering of Animatable Avatars (CVPR 2024 · similarity 0.88)
- Single-view Image to Novel-view Generation for Hand-Object Interactions (AAAI 2025 · similarity 0.87)
- SplattingAvatar: Realistic Real-Time Human Avatars with Mesh-Embedded Gaussian Splatting (CVPR 2024 · similarity 0.87)
- HOGSA: Bimanual Hand-Object Interaction Understanding with 3D Gaussian Splatting Based Data Augmentation (AAAI 2025 · similarity 0.87)
- MANUS: Markerless Grasp Capture using Articulated 3D Gaussians (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.
