Research map / 3D vision / Gaussian splatting
KineticGS: Momentum-driven Coherent 4D Gaussian Splatting for Monocular Dynamic Scene Reconstruction
Yunqing Wang, Baoyao Yang, SI-QI LIU, CHONG YIN, Yihua Shao, Hao Tang
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 momentum-guided particle initialization (ablation) | KineticGS · DyCheck-iPhone dynamic regions | mPSNR: 19.17 -> 19.68 | Improved |
| add momentum-guided initialization (ablation) | KineticGS · DyCheck-iPhone dynamic regions | mLPIPS: 0.141 -> 0.138 | Improved |
| add learnable energy-flow activation (ablation) | KineticGS · DyCheck-iPhone dynamic regions | mPSNR: 19.68 -> 19.76 | Improved |
| add learnable energy-flow activation (ablation) | KineticGS · DyCheck-iPhone dynamic regions | mLPIPS: 0.138 -> 0.134 | Improved |
| add holistic kinetic synchronization (ablation) | KineticGS · DyCheck-iPhone dynamic regions | mPSNR: 19.76 -> 20.12 | Improved |
| add holistic kinetic synchronization (ablation) | KineticGS · DyCheck-iPhone dynamic regions | mLPIPS: 0.134 -> 0.136 | Hurt |
| use space-filling-curve neighborhoods instead of KNN (k=8) (ablation) | KineticGS · DyCheck-iPhone overall | PSNR: 14.53 -> 14.65 | Improved |
| use space-filling-curve neighborhoods instead of voxel base (ablation) | KineticGS · DyCheck-iPhone overall | SSIM: 0.335 -> 0.342 | Improved |
| use KineticGS instead of MoDec-GS | Gaussian splatting · DyCheck-iPhone dynamic regions | mPSNR: 19.21 -> 20.12 | Improved |
| use KineticGS instead of MoDec-GS | Gaussian splatting · HyperNeRF-interp overall | mLPIPS: 0.219 -> 0.221 | Hurt |
| use KineticGS instead of MoDec-GS | Gaussian splatting · DyCheck-iPhone, Space-out | mPSNR: 17.64 -> 18.63 | 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 6 of 6 shared results
- SC-GS — SC-GS: Sparse-Controlled Gaussian Splatting for Editable Dynamic Scenes (CVPR 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
- MotionGS: Exploring Explicit Motion Guidance for Deformable 3D Gaussian Splatting (NeurIPS 2024 · similarity 0.92)
- Fully Explicit Dynamic Gaussian Splatting (NeurIPS 2024 · similarity 0.91)
- Motion Decoupled 3D Gaussian Splatting for Dynamic Object Representation (AAAI 2025 · similarity 0.91)
- 4D Gaussian Splatting in the Wild with Uncertainty-Aware Regularization (NeurIPS 2024 · similarity 0.90)
- Gaussian Splatting Lucas-Kanade (ICLR 2025 · similarity 0.90)
- Orientation-anchored Hyper-Gaussian for 4D Reconstruction from Casual Videos (NeurIPS 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.
