Research map / 3D vision / Gaussian splatting
Dynamic Texture Modeling of 3D Clothed Gaussian Avatars from a Single Video
Seungeun Lee, SeungJun Moon, Hah Min Lew, Ji-Su Kang, Gyeong-Moon Park
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 physics-inspired finite-difference dynamics with regularization (ablation) | GNN deformer · 4D-Dress | PSNR: 25.21 -> 26.05 | Improved |
| add adaptive spring stiffness (ablation) | GNN deformer · 4D-Dress | PSNR: 26.05 -> 26.44 | Improved |
| add edge-feature message passing (ablation) | GNN deformer · 4D-Dress | PSNR: 26.44 -> 27.12 | Improved |
| add velocity encoding with window 11 (ablation) | SMAGA · 4D-Dress | PSNR: 22.06 -> 27.89 | Improved |
| lengthen velocity window from 11 to 15 (ablation) | SMAGA · 4D-Dress | PSNR: 27.89 -> 26.78 | Hurt |
| add SMAD module (40k nodes) (ablation) | SMAGA · 4D-Dress | PSNR: 24.29 -> 27.89 | Improved |
| increase graph nodes from 40k to 100k (ablation) | SMAD · 4D-Dress | PSNR: 27.89 -> 27.02 | Hurt |
| use GNN instead of MLP deformer (ablation) | SMAD · 4D-Dress test motions | PSNR: 25.46 -> 27.89 | Improved |
| proposed SMAD vs vanilla GNN deformer (ablation) | SMAGA · 4D-Dress test motions | PSNR: 28.68 -> 27.89 | Mixed |
| add velocity encoding on 30s dynamic sequence (ablation) | SMAGA · 4D-Dress long sequence | PSNR: 24.47 -> 25.65 | Improved |
| SMAGA vs best baseline on loose clothing novel pose | SMAGA · 4D-Dress subject 00148 | PSNR: 22.79 -> 24.74 | Improved |
| SMAGA vs best baseline on novel pose, subject 00190 | SMAGA · 4D-Dress subject 00190 | LPIPS: 0.0278 -> 0.0347 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- 3DGS-Avatar — 3DGS-Avatar: Animatable Avatars via Deformable 3D Gaussian Splatting (CVPR 2024) · better on 6 of 8 shared results
- GART — GART: Gaussian Articulated Template Models (CVPR 2024) · 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
- Human Gaussian Splatting: Real-time Rendering of Animatable Avatars (CVPR 2024 · similarity 0.92)
- 3DGS-Avatar: Animatable Avatars via Deformable 3D Gaussian Splatting (CVPR 2024 · similarity 0.91)
- MPMAvatar: Learning 3D Gaussian Avatars with Accurate and Robust Physics-Based Dynamics (NeurIPS 2025 · similarity 0.91)
- Animatable Gaussians: Learning Pose-dependent Gaussian Maps for High-fidelity Human Avatar Modeling (CVPR 2024 · similarity 0.90)
- Gaussian Head & Shoulders: High Fidelity Neural Upper Body Avatars with Anchor Gaussian Guided Texture Warping (ICLR 2025 · similarity 0.90)
- FreeCloth: Free-form Generation Enhances Challenging Clothed Human Modeling (CVPR 2025 · similarity 0.89)
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.
