Research map / Image generation / Image restoration
FSI: Frequency and Spatial Interactive Learning for Image Restoration in Under-Display Cameras
Chengxu Liu, Xuan Wang, Shuai Li, Yuzhi Wang, Xueming Qian
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 spatial and frequency learning blocks to the ResBlock base (ablation) | FSI · SYNTH | PSNR: 44.84 -> 45.79 | Improved |
| add dual transfer unit between frequency and spatial streams (ablation) | FSI · SYNTH | PSNR: 45.79 -> 46.05 | Improved |
| add color transform module (ablation) | FSI · SYNTH | PSNR: 46.05 -> 46.14 | Improved |
| increase number of FSJ modules from 2 to 6 (ablation) | FSI · SYNTH | PSNR: 40.48 -> 46.14 | Improved |
| increase FSJ modules from 6 to 8 (ablation) | FSI · SYNTH | PSNR: 46.14 -> 46.41 | No clear effect |
| increase channels from 96 to 112 (ablation) | FSI · SYNTH | PSNR: 46.14 -> 46.23 | No clear effect |
| increase channels from 72 to 96 (ablation) | FSI · SYNTH | PSNR: 45.49 -> 46.14 | Improved |
| frequency-spatial interactive learning versus spatial-only BNUDC | FSI · SYNTH | PSNR: 45.78 -> 46.14 | Improved |
| FSI versus BNUDC on P-OLED | FSI · P-OLED | PSNR: 33.39 -> 33.85 | Improved |
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.
- BNUDC — BNUDC: A Two-Branched Deep Neural Network for Restoring Images From Under-Display Cameras (CVPR 2022) · better on 4 of 4 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
- Decoupling Degradations with Recurrent Network for Video Restoration in Under-Display Camera (AAAI 2024 · similarity 0.88)
- BNUDC: A Two-Branched Deep Neural Network for Restoring Images From Under-Display Cameras (CVPR 2022 · similarity 0.88)
- Beyond Spatial Domain: Cross-domain Promoted Fourier Convolution Helps Single Image Dehazing (AAAI 2025 · similarity 0.85)
- From Zero to Detail: Deconstructing Ultra-High-Definition Image Restoration from Progressive Spectral Perspective (CVPR 2025 · similarity 0.84)
- RIFLE: Removal of Image Flicker-Banding via Latent Diffusion Enhancement (NeurIPS 2026 · similarity 0.84)
- Efficient RAW Image Deblurring with Adaptive Frequency Modulation (NeurIPS 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.
