Research map / Image generation / Super-resolution
Contourlet Residual for Prompt Learning Enhanced Infrared Image Super-Resolution
Xingyuan Li, Jinyuan Liu, ZHIXIN CHEN, Yang Zou, Long Ma, Xin Fan, 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 both LP and DFB in the Contourlet residual instead of one (ablation) | CoRPLE · M3FD Set5 x4 | PSNR: 40.517 -> 40.779 | Improved |
| add positive text prompt (ablation) | CoRPLE · M3FD Set5 x4 | PSNR: 40.342 -> 40.731 | Improved |
| add negative prompt on top of positive prompt (ablation) | CoRPLE · M3FD Set5 x4 | PSNR: 40.731 -> 40.779 | Improved |
| learn prompts in stage one rather than fixing them (ablation) | CoRPLE · M3FD Set5 x4 | PSNR: 40.655 -> 40.779 | Improved |
| increase Contourlet levels from 1 to 4 (ablation) | CoRPLE · M3FD Set5 x4 | PSNR: 40.735 -> 40.779 | Improved |
| add both spatial and channel self-attention (ablation) | CoRPLE · M3FD x4 visual | visual quality | Improved |
| CoRPLE versus DAT at x4 on Set15 and Set20 | CoRPLE · M3FD Set15 x4 | PSNR: 40.812 (DAT) vs 40.765 | Hurt |
| CoRPLE versus HAT-L at x2 on Set5 | CoRPLE · M3FD Set5 x2 | PSNR: 48.584 (HAT-L) vs 48.581 | Hurt |
Closest papers by meaning
- Contourlet Refinement Gate Framework for Thermal Spectrum Distribution Regularized Infrared Image Super-Resolution (IJCV 2025 · similarity 0.93)
- Enhancing Infrared Vision: Progressive Prompt Fusion Network and Benchmark (NeurIPS 2025 · similarity 0.88)
- DifIISR: A Diffusion Model with Gradient Guidance for Infrared Image Super-Resolution (CVPR 2025 · similarity 0.85)
- Low-Res Leads the Way: Improving Generalization for Super-Resolution by Self-Supervised Learning (CVPR 2024 · similarity 0.84)
- ResDiff: Combining CNN and Diffusion Model for Image Super-resolution (AAAI 2024 · similarity 0.84)
- Beyond Image Super-Resolution for Image Recognition with Task-Driven Perceptual Loss (CVPR 2024 · 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.
