Research map / 3D vision / Gaussian splatting
Learning Explicit Continuous Motion Representation for Dynamic Gaussian Splatting from Monocular Videos
Xuankai Zhang, Junjin Xiao, Shangwei Huang, Wei-shi Zheng, Qing Zhang
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 control of motion bases (ablation) | SE(3) B-spline GS · iPhone | mPSNR: 18.84 -> 20.17 | Improved |
| add soft segment reconstruction (ablation) | SE(3) B-spline GS · iPhone | mSSIM: 0.628 -> 0.729 | Improved |
| add multi-view SDS loss (ablation) | SE(3) B-spline GS · iPhone | mPSNR: 19.39 -> 20.17 | Improved |
| add camera smoothness loss (ablation) | SE(3) B-spline GS · NVIDIA | LPIPS: 0.076 -> 0.049 | Improved |
| use SE(3) B-spline motion bases instead of SoM pose transformation (ablation) | SE(3) B-spline GS · iPhone | mPSNR: 18.17 -> 20.17 | Improved |
| use SE(3) B-spline motion bases instead of MoSca motion scaffolds (ablation) | SE(3) B-spline GS · iPhone | mPSNR: 19.26 -> 20.17 | Improved |
| perturb the 2D tracking prior with random noise (ablation) | SE(3) B-spline GS · iPhone | mPSNR: 20.17 -> 20.11 | No clear effect |
| compare to SplineGS on NVIDIA | SE(3) B-spline GS · NVIDIA | SSIM: 0.872 -> 0.871 | No clear effect |
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.
- MoSca — MoSca: Dynamic Gaussian Fusion from Casual Videos via 4D Motion Scaffolds (CVPR 2025) · better on 4 of 5 shared results
- HiMoR — HiMoR: Monocular Deformable Gaussian Reconstruction with Hierarchical Motion Representation (CVPR 2025) · better on 4 of 4 shared results
- SplineGS — SplineGS: Robust Motion-Adaptive Spline for Real-Time Dynamic 3D Gaussians from Monocular Video (CVPR 2025) · 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
- SC-GS: Sparse-Controlled Gaussian Splatting for Editable Dynamic Scenes (CVPR 2024 · similarity 0.92)
- Efficient Gaussian Splatting for Monocular Dynamic Scene Rendering via Sparse Time-Variant Attribute Modeling (AAAI 2025 · similarity 0.91)
- Motion Decoupled 3D Gaussian Splatting for Dynamic Object Representation (AAAI 2025 · similarity 0.91)
- MoDGS: Dynamic Gaussian Splatting from Casually-captured Monocular Videos with Depth Priors (ICLR 2025 · similarity 0.91)
- SplineGS: Robust Motion-Adaptive Spline for Real-Time Dynamic 3D Gaussians from Monocular Video (CVPR 2025 · similarity 0.91)
- MoDec-GS: Global-to-Local Motion Decomposition and Temporal Interval Adjustment for Compact Dynamic 3D Gaussian Splatting (CVPR 2025 · similarity 0.91)
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.
