Research map / 3D vision / Gaussian splatting
Let it Snow! Animating 3D Gaussian Scenes with Dynamic Weather Effects via Physics-Guided Score Distillation
Gal Fiebelman, Hadar Averbuch-Elor, Sagie Benaim
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 mesh-based collision handling (ablation) | Physics-Guided Score Distillation · All weather effects | VE-Bench: 0.34 -> 0.41 | Improved |
| add Video-SDS appearance optimization on top of physics simulation (ablation) | Physics-Guided Score Distillation · All weather effects | VE-Bench: 0.37 -> 0.41 | Improved |
| add physics simulation motion prior (ablation) | Video-SDS on 4DGS · All weather effects | VQAScore: 0.35 -> 0.89 | Improved |
| add physics guidance (joint optimization, regularization, conditioning) (ablation) | Physics-Guided Score Distillation · All weather effects | VQAScore: 0.85 -> 0.89 | Improved |
| add physics guidance (ablation) | Physics-Guided Score Distillation · All weather effects | CLIPSim: 0.26 -> 0.28 | Improved |
| dynamic particle emission vs static editing (GaussCtrl) | GaussCtrl · Fog+Snow edits | VQAScore: 0.71 -> 0.92 | Improved |
| vs ClimateNeRF on fog and snow | ClimateNeRF · Fog+Snow edits | VQAScore: 0.87 -> 0.92 | Improved |
| vs Instruct-4DGS without motion prior | Instruct-4DGS · All weather effects | VE-Bench: 0.19 -> 0.41 | 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.
- GaussCtrl — GaussCtrl: Multi-View Consistent Text-Driven 3D Gaussian Splatting Editing (ECCV 2024) · better on 6 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
- RainyGS: Efficient Rain Synthesis with Physically-Based Gaussian Splatting (CVPR 2025 · similarity 0.87)
- Fully Explicit Dynamic Gaussian Splatting (NeurIPS 2024 · similarity 0.87)
- HiCoM: Hierarchical Coherent Motion for Dynamic Streamable Scenes with 3D Gaussian Splatting (NeurIPS 2024 · similarity 0.86)
- Align Your Gaussians: Text-to-4D with Dynamic 3D Gaussians and Composed Diffusion Models (CVPR 2024 · similarity 0.86)
- H3D-DGS: Exploring Heterogeneous 3D Motion Representation for Deformable 3D Gaussian Splatting (NeurIPS 2025 · similarity 0.86)
- Gaussian Splashing: Unified Particles for Versatile Motion Synthesis and Rendering (CVPR 2025 · 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.
