Research map / Image generation / Image restoration
GridDehazeNet: Attention-Based Multi-Scale Network for Image Dehazing
Xiaohong Liu, Yongrui Ma, Zhihao Shi, Jun Chen
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 |
|---|---|---|---|
| estimate dehazed image directly instead of via the atmosphere scattering model (ablation) | GridDehazeNet · SOTS Indoor | PSNR: 30.33 -> 32.16 | Improved |
| estimate dehazed image directly instead of via the atmosphere scattering model (ablation) | GridDehazeNet · SOTS Outdoor | PSNR: 30.12 -> 30.86 | Improved |
| use direct estimation (ablation) | GridDehazeNet · Sun RGB-D | PSNR: 27.82 -> 28.67 | Improved |
| add learned pre-processing module instead of raw RGB inputs (ablation) | GridDehazeNet · SOTS Indoor | PSNR: 31.48 -> 32.16 | Improved |
| add learned pre-processing module instead of raw RGB inputs (ablation) | GridDehazeNet · SOTS Outdoor | PSNR: 30.33 -> 30.86 | Improved |
| use learned inputs instead of hand-selected derived inputs (ablation) | GridDehazeNet · SOTS Indoor | PSNR: 30.21 -> 32.16 | Improved |
| use hand-selected derived inputs instead of raw RGB (ablation) | GridDehazeNet · SOTS Indoor | PSNR: 31.48 -> 30.21 | Hurt |
| increase grid from 1 row, 6 columns to 3 rows, 6 columns (ablation) | GridDehazeNet · SOTS Indoor | PSNR: 25.95 -> 32.16 | Improved |
| increase columns from 2 to 6 at 3 rows (ablation) | GridDehazeNet · SOTS Indoor | PSNR: 22.57 -> 32.16 | Improved |
| add channel-wise attention to feature fusion (ablation) | GridDehazeNet · SOTS Indoor | PSNR: 31.77 -> 32.16 | Improved |
| add exchange branches between scales (ablation) | GridDehazeNet · SOTS Indoor | PSNR: 29.57 -> 32.16 | Improved |
| add post-processing module (ablation) | GridDehazeNet · SOTS Indoor | PSNR: 31.62 -> 32.16 | Improved |
Closest papers by meaning
- AOD-Net: All-In-One Dehazing Network (ICCV 2017 · similarity 0.89)
- Learning Hazing to Dehazing: Towards Realistic Haze Generation for Real-World Image Dehazing (CVPR 2025 · similarity 0.89)
- Dehaze-RetinexGAN: Real-World Image Dehazing via Retinex-based Generative Adversarial Network (AAAI 2025 · similarity 0.88)
- Real-world Image Dehazing with Coherence-based Pseudo Labeling and Cooperative Unfolding Network (NeurIPS 2024 · similarity 0.88)
- PromptHaze: Prompting Real-world Dehazing via Depth Anything Model (AAAI 2025 · similarity 0.87)
- Tokenize Image Patches: Global Context Fusion for Effective Haze Removal in Large Images (CVPR 2025 · similarity 0.86)
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.
