AI Paper Atlas

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

CVPR 2026 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Cross-domain few-shot with transformers

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 changedWhereMeasuredEffect
add manifold traversal dehazing loss L_dmt (ablation)CIM-D · SOTSPSNR: 21.15 -> 25.51Improved
add scattering semantics alignment loss L_ssa (ablation)CIM-D · SOTSPSNR: 22.89 -> 25.51Improved
add channel-decoupling regularization L_cdr (ablation)CIM-D · SOTSPSNR: 23.26 -> 25.51Improved
add spectrally-balanced scattering constraint L_asm (ablation)CIM-D · SOTSPSNR: 20.57 -> 25.51Improved
add hue-consistency loss L_hc (ablation)CIM-D · SOTSPSNR: 23.82 -> 25.51Improved
use continuous Cartesian HSV representation instead of raw HSV inputs (ablation)CIM-D · SOTSPSNR: 18.95 -> 25.51Improved
use residual decoupling blocks instead of standard residual blocks (ablation)CIM-D · SOTSPSNR: 24.18 -> 25.51Improved
CIM-D versus C2P on SOTSC2P · SOTSPSNR: 27.22 -> 25.51Hurt
CIM-D versus best baseline on Raw2ahC2P · Raw2ahPSNR: 17.26 -> 17.89Improved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy