Research map / Image generation / Super-resolution
Toward Real-world Infrared Image Super-Resolution: A Unified Autoregressive Framework and Benchmark Dataset
Yang Zou, Jun Ma, Zhidong Jiao, Xingyuan Li, Zhiying Jiang, Jinyuan Liu
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 |
|---|---|---|---|
| replace VAR backbone with ResShift diffusion (same TSG guidance) (ablation) | Real-IISR · FLIR-IISR | PSNR: 28.5126 -> 23.8670 (VAR vs diffusion) | Hurt |
| use VAR backbone instead of diffusion backbone (ablation) | Real-IISR · FLIR-IISR | MUSIQ: 50.3125 -> 59.9000 | Improved |
| add Thermal-Structural Guidance (TSG) (ablation) | Real-IISR · FLIR-IISR and M3FD | PSNR/SSIM/MUSIQ | Improved |
| add Condition-Adaptive Codebook (CAC) (ablation) | Real-IISR · FLIR-IISR and M3FD | MUSIQ, SSIM | Improved |
| add Thermal Order Consistency Loss (ablation) | Real-IISR · FLIR-IISR and M3FD | MUSIQ | Improved |
| Real-IISR vs VARSR (concise architecture, no diffusion refiner) | VAR-based SR · FLIR-IISR | inference speed: 6% faster | Improved |
| Real-IISR vs best baselines on M3FD PSNR | Real-IISR · M3FD Set5/Set15 | PSNR: 32.3175 vs 35.9204 (BI-DiffSR); 31.5633 vs 34.8666 | Hurt |
| Real-IISR vs baselines on M3FD MANIQA | Real-IISR · M3FD Set5/Set15 | MANIQA: 0.2532 vs 0.2801 (DifIISR) on Set5; 0.3074 vs 0.3348 (SinSR) on Set15 | Mixed |
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.
- DifIISR — DifIISR: A Diffusion Model with Gradient Guidance for Infrared Image Super-Resolution (CVPR 2025) · better on 10 of 12 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-Physics Guided Infrared Image Super-Resolution with Dynamic High-Frequency Amplification (AAAI 2026 · similarity 0.91)
- Contourlet Refinement Gate Framework for Thermal Spectrum Distribution Regularized Infrared Image Super-Resolution (IJCV 2025 · similarity 0.90)
- NSARM: Next-Scale Autoregressive Modeling for Robust Real-World Image Super-Resolution (NeurIPS 2026 · similarity 0.87)
- DifIISR: A Diffusion Model with Gradient Guidance for Infrared Image Super-Resolution (CVPR 2025 · similarity 0.86)
- Enhancing Infrared Vision: Progressive Prompt Fusion Network and Benchmark (NeurIPS 2025 · similarity 0.86)
- Unsupervised Diffusion-Based Degradation Modeling for Real-World Super-Resolution (AAAI 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.
