Research map / 3D vision / Gaussian splatting
Dynamic-Static Decomposition for Novel View Synthesis of Dynamic Scenes with Spiking Neurons
Lingyun Dai, Zehao Chen, Yan Liu, Shi Gu, Peng Lin, De Ma, Huajin Tang, Qian Zheng, Gang Pan
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 spatio-temporally fine-grained 4D mask field (ablation) | dynamic-static Gaussians with spiking neuron · N3DV cut beef (side view) | PSNR: 25.23 -> 25.50 | Improved |
| add spiking neuron discontinuous tagging (ablation) | dynamic-static Gaussians with 4D mask field · N3DV cut beef (side view) | PSNR: 25.50 -> 26.39 | Improved |
| use spiking neuron instead of Swift4D-style tag (Variant A) (ablation) | tagging field · N3DV cut beef (side view) | LPIPS: 0.0757 -> 0.0656 | Improved |
| use spiking neuron instead of sigmoid+threshold (Variant B) (ablation) | tagging field · N3DV cut beef (side view) | PSNR: 25.93 -> 26.39 | Improved |
| add 4D mask field and spiking neuron together (ablation) | dynamic-static baseline · N3DV cut beef (side view) | FPS: 95 -> 140 | Improved |
| use proposed method instead of Swift4D | dynamic NVS · VRU | PSNR: 29.03 -> 29.43 | Improved |
| use proposed method instead of Swift4D | dynamic NVS · VRU | FPS: 77 -> 77 | No clear effect |
| use proposed method instead of 4DGS | dynamic NVS · MeetRoom (side view) | PSNR: 26.27 -> 26.64 | Improved |
| use proposed method instead of 3DGStream | dynamic NVS · N3DV (side view) | FPS: 230 -> 137 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 2 on most shared results.
- Swift4D — Swift4D: Adaptive divide-and-conquer Gaussian Splatting for compact and efficient reconstruction of dynamic scene (ICLR 2025) · better on 8 of 8 shared results
- 3DGStream — 3DGStream: On-the-Fly Training of 3D Gaussians for Efficient Streaming of Photo-Realistic Free-Viewpoint Videos (CVPR 2024) · better on 2 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 0.87)
- Swift4D: Adaptive divide-and-conquer Gaussian Splatting for compact and efficient reconstruction of dynamic scene (ICLR 2025 · similarity 0.87)
- Spacetime Gaussian Feature Splatting for Real-Time Dynamic View Synthesis (CVPR 2024 · similarity 0.86)
- Efficient Gaussian Splatting for Monocular Dynamic Scene Rendering via Sparse Time-Variant Attribute Modeling (AAAI 2025 · similarity 0.86)
- FreeTimeGS: Free Gaussian Primitives at Anytime Anywhere for Dynamic Scene Reconstruction (CVPR 2025 · similarity 0.86)
- Real-time Photorealistic Dynamic Scene Representation and Rendering with 4D Gaussian Splatting (ICLR 2024 · similarity 0.86)
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.
