Research map / 3D vision / Gaussian splatting
Relaxed Rigidity with Ray-based Grouping for Dynamic Gaussian Splatting
Junoh Lee, Junmyeong Lee, Yeon-Ji Song, Inhwan Bae, Jisu Shin, Hae-Gon Jeon, Jin-Hwa Kim
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 ray-grouped motion coherence and spectral regularization | MoDec-GS · D-NeRF (7 scenes) | PSNR: 29.33 -> 31.68 | Improved |
| add ray-grouped regularization | Ex4DGS · D-NeRF (7 scenes) | PSNR: 29.93 -> 31.04 | Improved |
| add ray-grouped regularization | Grid4D · D-NeRF (7 scenes) | PSNR: 42.00 -> 42.20 | Improved |
| add ray-grouped regularization | RTD · HyperNeRF (vrig) | PSNR: 25.17 -> 25.30 | Improved |
| add ray-grouped regularization | MoDec-GS · NeRF-DS | PSNR: 22.93 -> 23.76 | Improved |
| use ray-based grouping instead of KNN with full regularization (ablation) | RTD · D-NeRF (RTD ablation, avg) | PSNR: 33.29 -> 36.46 | Improved |
| use ray-based grouping instead of KNN with ARAP (ablation) | RTD · HyperNeRF (RTD ablation, avg) | PSNR: 23.18 -> 25.25 | Improved |
| add ARAP rigidity with ray grouping (ablation) | RTD · D-NeRF (RTD ablation, avg) | PSNR: 35.36 -> 35.27 | No clear effect |
| MCR only versus MCR+SR (ablation) | RTD · HyperNeRF (RTD ablation, avg) | PSNR: 24.23 -> 25.30 | Improved |
| add spectral regularization to MCR (ablation) | RTD · D-NeRF (RTD ablation, avg) | PSNR: 36.23 -> 36.46 | Improved |
| spectral regularization only without MCR (ablation) | RTD · D-NeRF (RTD ablation, avg) | PSNR: 35.36 -> 34.98 | Hurt |
| add ray grouping regularization overhead (ablation) | RTD · D-NeRF (RTD ablation, avg) | training time (s): 841 -> 1924 | 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.
- MoDec-GS — MoDec-GS: Global-to-Local Motion Decomposition and Temporal Interval Adjustment for Compact Dynamic 3D Gaussian Splatting (CVPR 2025) · better on 3 of 3 shared results
- Grid4D — Grid4D: 4D Decomposed Hash Encoding for High-Fidelity Dynamic Gaussian Splatting (NeurIPS 2024) · 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
- Motion Decoupled 3D Gaussian Splatting for Dynamic Object Representation (AAAI 2025 · similarity 0.90)
- Efficient Gaussian Splatting for Monocular Dynamic Scene Rendering via Sparse Time-Variant Attribute Modeling (AAAI 2025 · similarity 0.90)
- MoDec-GS: Global-to-Local Motion Decomposition and Temporal Interval Adjustment for Compact Dynamic 3D Gaussian Splatting (CVPR 2025 · similarity 0.90)
- Orientation-anchored Hyper-Gaussian for 4D Reconstruction from Casual Videos (NeurIPS 2025 · similarity 0.90)
- 4D Gaussian Splatting in the Wild with Uncertainty-Aware Regularization (NeurIPS 2024 · similarity 0.90)
- HiCoM: Hierarchical Coherent Motion for Dynamic Streamable Scenes with 3D Gaussian Splatting (NeurIPS 2024 · similarity 0.90)
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.
