Research map / Image generation / Image restoration
Varicolored Image De-Hazing
Akshay Dudhane, Kuldeep M. Biradar, Prashant W. Patil, Praful Hambarde, Subrahmanyam Murala
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 the proposed network instead of RIGAN | Image de-hazing · D-Hazy | SSIM: 0.8179 -> 0.8901 | Improved |
| Use the proposed network instead of FAMED-Net | Image de-hazing · SOTS | PSNR: 27.0100 -> 28.2688 | Improved |
| Use two generators with dependent learning rather than one generator with combined loss (ablation) | Varicolored image de-hazing network · Dense-haze validation set | SSIM: 0.4572 -> 0.5538 | Improved |
| Use two generators with dependent learning rather than two generators with independent learning (ablation) | Varicolored image de-hazing network · Dense-haze validation set | SSIM: 0.4834 -> 0.5538 | Improved |
| Use two generators with dependent learning rather than two generators with combined learning (ablation) | Varicolored image de-hazing network · Dense-haze validation set | SSIM: 0.4902 -> 0.5538 | Improved |
| Add SSIM loss to L1 and edge losses (ablation) | Network-IV · Dense-haze validation set | SSIM: 0.4789 -> 0.5538 | Improved |
| Add edge loss to L1 and SSIM losses (ablation) | Network-IV · Dense-haze validation set | SSIM: 0.4879 -> 0.5538 | Improved |
| Add the HCC color-correction module rather than relying on gray-world color correction (ablation) | Varicolored image de-hazing network · Real-world varicolored hazy images | color balance | Improved |
Closest papers by meaning
- Physically Disentangled Intra- and Inter-Domain Adaptation for Varicolored Haze Removal (CVPR 2022 · similarity 0.88)
- Guided Real Image Dehazing Using YCbCr Color Space (AAAI 2025 · similarity 0.86)
- Single Image Dehazing Using Haze-Lines (TPAMI 2018 · similarity 0.86)
- Tokenize Image Patches: Global Context Fusion for Effective Haze Removal in Large Images (CVPR 2025 · similarity 0.84)
- PRISM: Rethinking Atmospheric Scattering Reconstruction as a Unified Understanding and Restoration Model for Real-world Dehazing (NeurIPS 2026 · similarity 0.84)
- Learning Hazing to Dehazing: Towards Realistic Haze Generation for Real-World Image Dehazing (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.
