Research map / 3D vision / Gaussian splatting
MoRGS: Efficient Per-Gaussian Motion Reasoning for Streamable Dynamic 3D Scenes
Wonjoon Lee, Sungmin Woo, Donghyeong Kim, Jungho Lee, Sangheon Park, Sangyoun Lee
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 sparse optical-flow motion learning (ablation) | MoRGS baseline · N3DV | PSNR: 31.33 -> 31.85 | Improved |
| add sparse optical-flow motion learning (ablation) | MoRGS baseline · Meet Room | PSNR: 29.40 -> 30.55 | Improved |
| add per-Gaussian motion offset field (ablation) | MoRGS (ML) · N3DV | PSNR: 31.85 -> 32.21 | Improved |
| add per-Gaussian motion offset field (ablation) | MoRGS (ML) · Meet Room | PSNR: 30.55 -> 31.21 | Improved |
| add per-Gaussian motion confidence (ablation) | MoRGS (ML+MO) · N3DV | PSNR: 32.21 -> 32.53 | Improved |
| add per-Gaussian motion confidence (ablation) | MoRGS (ML+MO) · Meet Room | PSNR: 31.21 -> 31.79 | Improved |
| increase supervised views from 2 to 8 (no offset) (ablation) | MoRGS w/o motion offset · N3DV | PSNR: 31.60 -> 32.07 | Improved |
| add motion offset with only 4 supervised views (ablation) | MoRGS · N3DV | PSNR: 31.95 -> 32.21 | Improved |
| add motion offset with 12 supervised views (ablation) | MoRGS · N3DV | PSNR: 32.12 -> 32.22 | No clear effect |
| train per-frame residuals 5 epochs instead of 8 (MoRGS-s) (ablation) | MoRGS-l · N3DV | PSNR: 32.53 -> 32.42 | Mixed |
| add motion learning cost in training time (ablation) | MoRGS baseline · N3DV | Train time (s): 3.3 -> 3.7 | 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.
- 3DGStream — 3DGStream: On-the-Fly Training of 3D Gaussians for Efficient Streaming of Photo-Realistic Free-Viewpoint Videos (CVPR 2024) · better on 3 of 3 shared results
- HiCoM — HiCoM: Hierarchical Coherent Motion for Dynamic Streamable Scenes with 3D Gaussian Splatting (NeurIPS 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
- Motion Matters: Compact Gaussian Streaming for Free-Viewpoint Video Reconstruction (NeurIPS 2025 · similarity 0.92)
- HiCoM: Hierarchical Coherent Motion for Dynamic Streamable Scenes with 3D Gaussian Splatting (NeurIPS 2024 · similarity 0.92)
- MotionGS: Exploring Explicit Motion Guidance for Deformable 3D Gaussian Splatting (NeurIPS 2024 · similarity 0.92)
- FreeTimeGS: Free Gaussian Primitives at Anytime Anywhere for Dynamic Scene Reconstruction (CVPR 2025 · similarity 0.91)
- Gaussian-Flow: 4D Reconstruction with Dynamic 3D Gaussian Particle (CVPR 2024 · similarity 0.91)
- Instant Gaussian Stream: Fast and Generalizable Streaming of Dynamic Scene Reconstruction via Gaussian Splatting (CVPR 2025 · 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.
