Research map / 3D vision / Gaussian splatting
Temporally Aware Densification for Dynamic 3D Gaussian Splatting
VIKRAM SANDU, Mayurdeep Pathak, Rajiv Soundararajan
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 visibility-aware densification (VAD) (ablation) | dynamic 3DGS (deformation baseline) · Interdigital | M-PSNR: 24.75 -> 27.32 | Improved |
| add temporally-adaptive thresholding (TAT) on top of VAD (ablation) | dynamic 3DGS · Interdigital | M-PSNR: 27.32 -> 27.51 | Improved |
| add temporal offset warping (TOW) (ablation) | dynamic 3DGS with VAD+TAT · Interdigital | M-PSNR: 27.51 -> 28.87 | Improved |
| add VAD (ablation) | dynamic 3DGS · N3DV | M-PSNR: 21.96 -> 23.40 | Improved |
| add TAT on top of VAD (ablation) | dynamic 3DGS · N3DV | PSNR: 32.14 -> 32.17 | No clear effect |
| add TOW (ablation) | dynamic 3DGS with VAD+TAT · N3DV | M-PSNR: 23.62 -> 24.68 | Improved |
| add VAD as plug-in | STG · N3DV | M-PSNR: 22.61 -> 24.01 | Improved |
| add VAD as plug-in | Swift4D · Interdigital | M-PSNR: 23.01 -> 23.31 | Improved |
| add VAD as plug-in | Swift4D · N3DV | LPIPS: 0.061 -> 0.061 | No clear effect |
| add VAD, TAT and TOW (ablation) | dynamic 3DGS · VRU Basketball | M-PSNR: 21.03 -> 25.39 | Improved |
| add VAD, TAT and TOW (ablation) | dynamic 3DGS · N3DV | model size (MB): 155 -> 204 | Hurt |
| lower the densification threshold instead of VAD (ablation) | 3DGS densification · N3DV | M-PSNR | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- Swift4D — Swift4D: Adaptive divide-and-conquer Gaussian Splatting for compact and efficient reconstruction of dynamic scene (ICLR 2025) · 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
- 4D Gaussian Splatting in the Wild with Uncertainty-Aware Regularization (NeurIPS 2024 · similarity 0.90)
- Perceptual-GS: Scene-adaptive Perceptual Densification for Gaussian Splatting (ICML 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)
- Efficient Gaussian Splatting for Monocular Dynamic Scene Rendering via Sparse Time-Variant Attribute Modeling (AAAI 2025 · similarity 0.90)
- Swift4D: Adaptive divide-and-conquer Gaussian Splatting for compact and efficient reconstruction of dynamic scene (ICLR 2025 · similarity 0.90)
- Motion Decoupled 3D Gaussian Splatting for Dynamic Object Representation (AAAI 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.
