Research map / Image generation / Super-resolution
3M-TI: High-Quality Mobile Thermal Imaging via Calibration-free Multi-Camera Cross-Modal Diffusion
Minchong Chen, Xiaoyun Yuan, Junzhe Wan, Jianing Zhang, Jun Zhang
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 misalignment augmentation (ablation) | 3M-TI · public test set | LPIPS: 0.1917 -> 0.1787 | Improved |
| add misalignment augmentation (ablation) | 3M-TI · public test set | MUSIQ: 34.94 -> 36.66 | Improved |
| add misalignment augmentation | CoReFusion / SwinFuSR / SwinPaste · public test set | PSNR: 30.11 -> 30.30 (CoReFusion) | No clear effect |
| add RGB reference (ablation) | 3M-TI · public test set | MUSIQ: 32.85 -> 36.66 | Improved |
| add RAM semantic prompt (ablation) | 3M-TI · public test set | LPIPS: 0.1805 -> 0.1787 | No clear effect |
| add skip connection (ablation) | 3M-TI · public test set | PSNR: 29.86 -> 30.09 | Improved |
| add skip connection (ablation) | 3M-TI · public test set | LPIPS: 0.1795 -> 0.1787 | No clear effect |
| use CSM instead of original self-attention (ablation) | 3M-TI · public test set | MUSIQ: 34.47 -> 36.66 | Improved |
| use CSM instead of feature concat + FC (ablation) | 3M-TI · public test set | PSNR: 29.60 -> 30.09 | Improved |
| use CSM instead of standard cross-attention (ablation) | 3M-TI · public test set | MUSIQ: 34.32 -> 36.66 | Improved |
| use 3M-TI-enhanced thermal for Grounded-SAM detection vs SeeSR thermal | 3M-TI · LLVIP+M3FD detection | F1-score: 0.3849 -> 0.4724 | Improved |
| use 3M-TI instead of DifIISR on fidelity | 3M-TI · public test set | PSNR: 27.48 -> 30.09 | Improved |
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.
- DifIISR — DifIISR: A Diffusion Model with Gradient Guidance for Infrared Image Super-Resolution (CVPR 2025) · better on 2 of 3 shared results
- SeeSR — SeeSR: Towards Semantics-Aware Real-World Image Super-Resolution (CVPR 2024) · better on 3 of 3 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
- Thermal Diffusion Matters: Infrared Spatial-Temporal Video Super-Resolution through Heat Conduction Priors (CVPR 2026 · similarity 0.87)
- ThermalGaussian++: Improving Alignment and Resolution for ThermalGaussian (TPAMI 2026 · similarity 0.86)
- Thermal-Aware Low-Light Image Enhancement: A Real-World Benchmark and a New Light-Weight Model (AAAI 2025 · similarity 0.86)
- ThermalGaussian: Thermal 3D Gaussian Splatting (ICLR 2025 · similarity 0.84)
- Edge-SD-SR: Low Latency and Parameter Efficient On-device Super-Resolution with Stable Diffusion via Bidirectional Conditioning (CVPR 2025 · similarity 0.84)
- ThermalGen: Style-Disentangled Flow-Based Generative Models for RGB-to-Thermal Image Translation (NeurIPS 2025 · similarity 0.83)
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.
