Research map / Label-efficient and robust learning / Domain adaptation and generalization
Disentanglement-wise Image Dehazing through Cross-Domain Manifold Consensus
Tianyi Lyu, Mingye Ju, Kai-Kuang Ma
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 manifold traversal dehazing loss L_dmt (ablation) | CIM-D · SOTS | PSNR: 21.15 -> 25.51 | Improved |
| add scattering semantics alignment loss L_ssa (ablation) | CIM-D · SOTS | PSNR: 22.89 -> 25.51 | Improved |
| add channel-decoupling regularization L_cdr (ablation) | CIM-D · SOTS | PSNR: 23.26 -> 25.51 | Improved |
| add spectrally-balanced scattering constraint L_asm (ablation) | CIM-D · SOTS | PSNR: 20.57 -> 25.51 | Improved |
| add hue-consistency loss L_hc (ablation) | CIM-D · SOTS | PSNR: 23.82 -> 25.51 | Improved |
| use continuous Cartesian HSV representation instead of raw HSV inputs (ablation) | CIM-D · SOTS | PSNR: 18.95 -> 25.51 | Improved |
| use residual decoupling blocks instead of standard residual blocks (ablation) | CIM-D · SOTS | PSNR: 24.18 -> 25.51 | Improved |
| CIM-D versus C2P on SOTS | C2P · SOTS | PSNR: 27.22 -> 25.51 | Hurt |
| CIM-D versus best baseline on Raw2ah | C2P · Raw2ah | PSNR: 17.26 -> 17.89 | Improved |
Closest papers by meaning
- Guided Real Image Dehazing Using YCbCr Color Space (AAAI 2025 · similarity 0.86)
- ODCR: Orthogonal Decoupling Contrastive Regularization for Unpaired Image Dehazing (CVPR 2024 · similarity 0.86)
- PRISM: Rethinking Atmospheric Scattering Reconstruction as a Unified Understanding and Restoration Model for Real-world Dehazing (NeurIPS 2026 · similarity 0.86)
- Learning Hazing to Dehazing: Towards Realistic Haze Generation for Real-World Image Dehazing (CVPR 2025 · similarity 0.85)
- Real-world Image Dehazing with Coherence-based Pseudo Labeling and Cooperative Unfolding Network (NeurIPS 2024 · similarity 0.85)
- Depth-Centric Dehazing and Depth-Estimation from Real-World Hazy Driving Video (AAAI 2025 · similarity 0.85)
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.
