Research map / Image generation / Image restoration
Decoupling-and-Aggregating for Image Exposure Correction
Yang Wang, Long Peng, Liang Li, Yang Cao, Zheng-Jun Zha
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 TConv with DAConv | ENC · ME dataset, under-exposure | PSNR: 22.720 -> 23.320+0.600 | Improved |
| Replace TConv with DAConv | ENC · SICE dataset, under-exposure | PSNR: 18.665 -> 19.072+0.407 | Improved |
| Replace TConv with DAConv | ENC · LOLV1 | PSNR: 22.310 -> 22.856+0.546 | Improved |
| Replace TConv with DAConv | ENC · LOL-V2-Real | PSNR: 21.004 -> 21.764+0.760 | Improved |
| Use DA and CA in series (ablation) | MSEC · ME dataset, under-exposure | PSNR: 20.520 -> 18.592 | Hurt |
| Use CA and DA in series (ablation) | MSEC · ME dataset, under-exposure | PSNR: 20.520 -> 18.950 | Hurt |
| Use two parallel TConv branches (ablation) | MSEC · ME dataset, under-exposure | PSNR: 20.520 -> 20.720 | Improved |
| Use parallel DA and TConv-minus-DA branches (ablation) | MSEC · ME dataset, under-exposure | PSNR: 20.520 -> 20.640 | Improved |
| Use parallel TConv and DA branches (ablation) | MSEC · ME dataset, under-exposure | PSNR: 20.520 -> 21.010 | Improved |
| Use parallel TConv and CA branches (ablation) | MSEC · ME dataset, under-exposure | PSNR: 20.520 -> 21.034 | Improved |
| Add dynamic branch coefficients to parallel DA and CA (ablation) | MSEC · ME dataset, under-exposure | PSNR: 21.256 -> 21.530 | Improved |
| Replace TConv with DAConv | RetinexNet · ME dataset, over-exposure | PSNR: 10.470 -> 18.576+8.106 | Improved |
Closest papers by meaning
- Region-Aware Exposure Consistency Network for Mixed Exposure Correction (AAAI 2024 · similarity 0.88)
- Exposure Normalization and Compensation for Multiple-Exposure Correction (CVPR 2022 · similarity 0.88)
- Learning Video Exposure Correction: Large-Scale Real-World Dataset and Method (TPAMI 2026 · similarity 0.88)
- CLIP-RestoreX: Restore Image Structure and Perception in Exposure Correction (AAAI 2025 · similarity 0.87)
- Real-Time Exposure Correction via Collaborative Transformations and Adaptive Sampling (CVPR 2024 · similarity 0.85)
- Exposure-slot: Exposure-centric Representations Learning with Slot-in-Slot Attention for Region-aware Exposure Correction (CVPR 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.
