Research map / 3D vision / Gaussian splatting
ETGS: Explicit Thermodynamics Gaussian Splatting for Dynamic Thermal Reconstruction
Zhongwen Wang, Han Ling, Weihao Zhang, Yinghui Sun, Quansen Sun
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 heat source excitation Q (ablation) | ETGS · Rapid Heat Dynamics (Cooling Checkboard) | PSNR: 43.70 -> 44.73 | Improved |
| add regularization term (ablation) | ETGS · Rapid Heat Dynamics (Cooling Checkboard) | PSNR: 42.58 -> 44.73 | Improved |
| add regularization term (ablation) | ETGS · Rapid Heat Dynamics (Cooling Checkboard) | LPIPS: 0.064 -> 0.054 | Improved |
| add heat source excitation Q (ablation) | ETGS · Rapid Heat Dynamics (Cooling Checkboard) | LPIPS: 0.055 -> 0.054 | Improved |
| add heat source excitation Q (ablation) | ETGS · Rapid Heat Dynamics (Cooling Checkboard) | training time (s): 181 -> 197 | Hurt |
| increase number of frequencies K from 8 to 64 (ablation) | ETGS · Rapid Heat Dynamics (avg) | PSNR: 40.57 -> 40.95 | Improved |
| increase number of frequencies K from 8 to 64 (ablation) | ETGS · Rapid Heat Dynamics (avg) | LPIPS: 0.050 -> 0.051 | No clear effect |
| use closed-form thermodynamic model instead of NTR-Gaussian | ETGS · Rapid Heat Dynamics (avg) | PSNR: 34.96 -> 40.68 | Improved |
| use ETGS instead of 4DGS | ETGS · Rapid Heat Dynamics (avg) | training time (s): 1159 -> 197 | Improved |
| use ETGS instead of 3DGS | ETGS · Rapid Heat Dynamics (avg) | PSNR: 32.16 -> 40.68 | Improved |
| use ETGS instead of NTR-Gaussian | ETGS · Rapid Heat Dynamics (avg) | FPS: 68 -> 458 | Improved |
| use ETGS instead of 3DGS | ETGS · Rapid Heat Dynamics (avg) | FPS: 557 -> 458 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- NTR-Gaussian — NTR-Gaussian: Nighttime Dynamic Thermal Reconstruction with 4D Gaussian Splatting Based on Thermodynamics (CVPR 2025) · better on 5 of 5 shared results
- Mip-Splatting — Mip-Splatting: Alias-free 3D Gaussian Splatting (CVPR 2024) · better on 4 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
- ThermalGaussian: Thermal 3D Gaussian Splatting (ICLR 2025 · similarity 0.89)
- Fully Explicit Dynamic Gaussian Splatting (NeurIPS 2024 · similarity 0.87)
- NTR-Gaussian: Nighttime Dynamic Thermal Reconstruction with 4D Gaussian Splatting Based on Thermodynamics (CVPR 2025 · similarity 0.86)
- Gaussian Splashing: Unified Particles for Versatile Motion Synthesis and Rendering (CVPR 2025 · similarity 0.86)
- Temporal Smoothness-Aware Rate-Distortion Optimized 4D Gaussian Splatting (NeurIPS 2025 · similarity 0.85)
- Fast Feedforward 3D Gaussian Splatting Compression (ICLR 2025 · similarity 0.85)
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.
