Research map / 3D vision / Gaussian splatting
Thermal3D-GS: Physics-induced 3D Gaussians for Thermal Infrared Novel-view Synthesis
Qian Chen, Shihao Shu, Xiangzhi Bai
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 Atmospheric Transmission Field (ATF) to 3D-GS (ablation) | 3D-GS · TI-NSD average | PSNR: 32.01 -> 34.33 | Improved |
| add Thermal Conduction Module (TCM) to 3D-GS (ablation) | 3D-GS · TI-NSD average | PSNR: 32.01 -> 32.70 | Improved |
| add discontinuous loss to 3D-GS (ablation) | 3D-GS · TI-NSD average | PSNR: PSNR 32.01 -> 32.76, SSIM 0.936 -> 0.909 | Mixed |
| combine ATF, TCM and discontinuous loss (full Thermal3D-GS) (ablation) | 3D-GS · TI-NSD average | PSNR: 32.01 -> 35.04 | Improved |
| use Thermal3D-GS instead of 3D-GS at 7k iterations | 3D-GS · TI-NSD average | PSNR: 29.64 -> 31.44 | Improved |
| use 3D-GS instead of NeRF-style methods (INGP, Plenoxels) | thermal novel view synthesis · TI-NSD average | PSNR: 24.91 -> 32.01 | Improved |
| use larger Instant-NGP network (Big vs Base) (ablation) | Instant-NGP · TI-NSD average | PSNR: 24.62 -> 24.91 | No clear effect |
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.
- Plenoxels — Plenoxels: Radiance Fields Without Neural Networks (CVPR 2022) · better on 1 of 1 shared result
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 0.91)
- NTR-Gaussian: Nighttime Dynamic Thermal Reconstruction with 4D Gaussian Splatting Based on Thermodynamics (CVPR 2025 · similarity 0.90)
- Wild-GS: Real-Time Novel View Synthesis from Unconstrained Photo Collections (NeurIPS 2024 · similarity 0.87)
- GS-IR: 3D Gaussian Splatting for Inverse Rendering (CVPR 2024 · similarity 0.86)
- Horizon-GS: Unified 3D Gaussian Splatting for Large-Scale Aerial-to-Ground Scenes (CVPR 2025 · similarity 0.86)
- COLMAP-Free 3D Gaussian Splatting (CVPR 2024 · 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.
