Research map / 3D vision / Gaussian splatting
MCGS: Markov Chain Gaussian Splatting for Dynamic Scenes Reconstruction
Yuzhong Wang, Wenmin Wang, Shixiong Zhang, Xinxing Yu, Zhongheng Chen
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 multi-head temporal attention over the sliding window of historical states (ablation) | MCGS · D-NeRF (800x800) | PSNR: 40.45 -> 42.74 | Improved |
| add multi-head temporal attention (ablation) | MCGS · D-NeRF (800x800) | FPS: 209 -> 174.75 | Hurt |
| add noise injection to Markov deformation predictions during training (ablation) | MCGS · D-NeRF (800x800) | PSNR: 41.59 -> 42.74 | Improved |
| use MCGS instead of SC-GS | MCGS · D-NeRF (800x800) | PSNR: 38.63 -> 42.74 | Improved |
| use MCGS instead of SP-GS | MCGS · D-NeRF (800x800) | training time: 32:53 -> 15:54 | Improved |
| use MCGS instead of SP-GS on HyperNeRF vrig | MCGS · HyperNeRF vrig | PSNR: 25.22 -> 25.76 | Improved |
| use MCGS instead of SP-GS on HyperNeRF vrig LPIPS | MCGS · HyperNeRF vrig | LPIPS: 0.2404 (SP-GS) vs 0.2427 (MCGS) | No clear effect |
| use MCGS rendering instead of SC-GS | MCGS · D-NeRF (800x800) | FPS: 186 -> 174.75 | 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.
- SC-GS — SC-GS: Sparse-Controlled Gaussian Splatting for Editable Dynamic Scenes (CVPR 2024) · better on 5 of 6 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
- Efficient Gaussian Splatting for Monocular Dynamic Scene Rendering via Sparse Time-Variant Attribute Modeling (AAAI 2025 · similarity 0.92)
- Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene Reconstruction (CVPR 2024 · similarity 0.91)
- HAIF-GS: Hierarchical and Induced Flow-Guided Gaussian Splatting for Dynamic Scene (NeurIPS 2025 · similarity 0.91)
- HiCoM: Hierarchical Coherent Motion for Dynamic Streamable Scenes with 3D Gaussian Splatting (NeurIPS 2024 · similarity 0.91)
- MoDGS: Dynamic Gaussian Splatting from Casually-captured Monocular Videos with Depth Priors (ICLR 2025 · similarity 0.90)
- Gaussian Splatting Lucas-Kanade (ICLR 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.
