Research map / 3D vision / Gaussian splatting
MOSAIC-GS: Monocular Scene Reconstruction via Advanced Initialization for Complex Dynamic Environments
Svitlana Morkva, Vaishakh Patil, Alessio Tonioni, Michael Oechsle, Maximum Wilder-Smith, Marco Hutter
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 |
|---|---|---|---|
| separate static and dynamic Gaussians (ablation) | MOSAIC-GS · DyCheck ablation | mPSNR: 14.65 -> 18.40 | Improved |
| initialize dynamic Gaussian deformation coefficients from scene flow (ablation) | MOSAIC-GS · DyCheck ablation | mPSNR: 16.99 -> 18.40 | Improved |
| add rigid scene flow refinement (ablation) | MOSAIC-GS · DyCheck ablation | mPSNR: 18.11 -> 18.40 | Improved |
| add depth Pearson correlation loss (ablation) | MOSAIC-GS · DyCheck ablation | mPSNR: 18.13 -> 18.40 | Improved |
| raise Fourier degree from 16 to 32 (ablation) | MOSAIC-GS · DyCheck ablation | mPSNR: 18.29 -> 18.40 | Improved |
| raise Fourier degree from 24 to 32 (ablation) | MOSAIC-GS · DyCheck ablation | mPSNR: 18.37 -> 18.40 | No clear effect |
| remove scene disentanglement (ablation) | MOSAIC-GS · DyCheck ablation | training time (min): 5.06 -> 8.26 | Hurt |
| MOSAIC-GS vs MoSca on fidelity | MOSAIC-GS · iPhone DyCheck | PSNR: 19.32 -> 18.4 | Mixed |
| MOSAIC-GS vs MoSca on speed | MOSAIC-GS · iPhone DyCheck | training time: 50 min -> 10.5 min | Improved |
| MOSAIC-GS vs Gaussian Marbles | MOSAIC-GS · NVIDIA Dynamic Scene (Gaussian Marbles variant) | PSNR: 23.68 -> 23.79 | Improved |
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.
- MoSca — MoSca: Dynamic Gaussian Fusion from Casual Videos via 4D Motion Scaffolds (CVPR 2025) · better on 4 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
- MoDGS: Dynamic Gaussian Splatting from Casually-captured Monocular Videos with Depth Priors (ICLR 2025 · similarity 0.92)
- World from Motion: Generative Dynamic Gaussian Reconstruction from Monocular Video (NeurIPS 2026 · similarity 0.92)
- Motion Decoupled 3D Gaussian Splatting for Dynamic Object Representation (AAAI 2025 · similarity 0.90)
- Efficient Gaussian Splatting for Monocular Dynamic Scene Rendering via Sparse Time-Variant Attribute Modeling (AAAI 2025 · similarity 0.90)
- SplineGS: Robust Motion-Adaptive Spline for Real-Time Dynamic 3D Gaussians from Monocular Video (CVPR 2025 · similarity 0.90)
- 4D Gaussian Splatting in the Wild with Uncertainty-Aware Regularization (NeurIPS 2024 · 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.
