Research map / Image generation / Image restoration
Deep Fourier-Based Exposure Correction Network with Spatial-Frequency Interaction
Jie Huang, Yajing Liu, Feng Zhao, Keyu Yan, Jinghao Zhang, Yukun Huang, Man Zhou, Zhiwei Xiong
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 the amplitude sub-network (ablation) | FECNet · SICE | PSNR (dB): 19.98 -> 20.96 | Improved |
| add the phase sub-network (ablation) | FECNet · SICE | PSNR (dB): 20.03 -> 20.96 | Improved |
| restore amplitude first then phase instead of phase first (ablation) | FECNet · SICE | PSNR (dB): 19.35 -> 20.96 | Improved |
| use matched SFI format per sub-network instead of swapped (ablation) | FECNet · SICE | PSNR (dB): 20.78 -> 20.96 | Improved |
| feed phase sub-network the recombination with original phase instead of amplitude output (ablation) | FECNet · SICE | PSNR (dB): 20.67 -> 20.96 | Improved |
| add lightness residual guidance to phase sub-network (ablation) | FECNet · SICE | PSNR (dB): 20.77 -> 20.96 | Improved |
| add amplitude-stage loss Ls1 to the baseline (ablation) | FECNet · SICE | PSNR (dB): 20.01 -> 20.83 | Improved |
| add amplitude supervision term in Ls1 (ablation) | FECNet · SICE | PSNR (dB): 20.43 -> 20.96 | Improved |
| add Ls2 phase loss to the baseline (ablation) | FECNet · SICE | PSNR (dB): 20.01 -> 20.03 | No clear effect |
| use SFI block instead of two spatial branches (ablation) | FECNet · SICE | PSNR (dB): 18.57 -> 20.96 | Improved |
| use SFI block instead of two frequency branches (ablation) | FECNet · SICE | PSNR (dB): 18.64 -> 20.96 | Improved |
| add interaction between spatial and frequency branches (ablation) | FECNet · SICE | PSNR (dB): 19.82 -> 20.96 | Improved |
Closest papers by meaning
- Decoupling-and-Aggregating for Image Exposure Correction (CVPR 2023 · similarity 0.87)
- CLIP-RestoreX: Restore Image Structure and Perception in Exposure Correction (AAAI 2025 · similarity 0.86)
- Fourier Priors-Guided Diffusion for Zero-Shot Joint Low-Light Enhancement and Deblurring (CVPR 2024 · similarity 0.86)
- Beyond Spatial Domain: Cross-domain Promoted Fourier Convolution Helps Single Image Dehazing (AAAI 2025 · similarity 0.86)
- Region-Aware Exposure Consistency Network for Mixed Exposure Correction (AAAI 2024 · similarity 0.85)
- Multi-Domain Multi-Scale Diffusion Model for Low-Light Image Enhancement (AAAI 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.
