Research map / Image generation / Image restoration
HiDRA: Hierarchical Degradation Representation and Adaptation with Generative Priors for Enhancing Infrared Vision
Zihang Chen, Zhu Liu, Changbo Yan, Jinyuan Liu, Risheng 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 |
|---|---|---|---|
| use the bi-level first-order solution instead of alternating optimization (ablation) | HiDRA · HM-TIR blind super-resolution | MANIQA: 0.530 -> 0.556 | Improved |
| use the bi-level first-order solution instead of alternating optimization (ablation) | HiDRA · HM-TIR FPN correction | MANIQA: 0.556 -> 0.572 | Improved |
| use upper-level bi-level training instead of joint training of DEM and base model (ablation) | HiDRA · HM-TIR FPN correction | MANIQA: 0.569 -> 0.572 | Improved |
| use upper-level bi-level training instead of joint training of DEM and base model (ablation) | HiDRA · HM-TIR blind super-resolution | MANIQA: 0.556 -> 0.556 | No clear effect |
| bi-level learning makes DEM embeddings separable by degradation level (ablation) | DEM · t-SNE of degradation vectors | cluster separability | Improved |
| increase number of degradation pipelines M from 2 to 3 (ablation) | HiDRA · HM-TIR blind SR, 256x256 patches | MANIQA: 0.500 -> 0.548 | Improved |
| increase number of degradation pipelines M from 3 to 4 (ablation) | HiDRA · HM-TIR blind SR, 256x256 patches | MANIQA: 0.548 -> 0.543 | Hurt |
| add DEM with MIA module to LoRA fine-tuning (ablation) | SD Turbo + LoRA · HM-TIR (Fig. 6a) | image quality metrics | Improved |
| replace deterministic composite-degradation framework (PPFN) with HiDRA at extreme degradation | HiDRA · Composite degradation (Extreme) | LPIPS: 0.550 -> 0.230 | Improved |
| use HiDRA enhancement before downstream detector | YOLOv8 on M3FD · M3FD object detection | mAP: 0.595 -> 0.619 | Improved |
| use HiDRA super-resolution before segmentation | SegFormer on FMB · FMB semantic segmentation | mIoU: 48.2 -> 49.4 | Improved |
| HiDRA versus PPFN on real-world no-reference fusion metrics | HiDRA · TNO / RoadScene real-world | QAB/F: 0.3916 -> 0.3912 (TNO) | Mixed |
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 5 of 5 shared results
- CDFormer — CDFormer: When Degradation Prediction Embraces Diffusion Model for Blind Image Super-Resolution (CVPR 2024) · better on 2 of 2 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
- Expandable, Compressible, Mineable: Open-World Thermal Infrared Image Restoration (ICML 2026 · similarity 0.88)
- Enhancing Infrared Vision: Progressive Prompt Fusion Network and Benchmark (NeurIPS 2025 · similarity 0.88)
- TherA: Thermal-Aware Visual-Language Prompting for Controllable RGB-to-Thermal Infrared Translation (CVPR 2026 · similarity 0.87)
- DEAL: Data-Efficient Adversarial Learning for High-Quality Infrared Imaging (CVPR 2025 · similarity 0.86)
- Continuous Adverse Weather Removal via Degradation-Aware Distillation (CVPR 2025 · similarity 0.85)
- Unsupervised Degradation Representation Aware Transform for Real-World Blind Image Super-Resolution (AAAI 2025 · similarity 0.84)
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.
