AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

Towards Real-World Adverse Weather Image Restoration: Enhancing Clearness and Semantics with Vision-Language Models

Jiaqi Xu, Mengyang Wu, Xiaowei Hu, Chi-Wing Fu, Qi Dou, Pheng-Ann Heng

ECCV 2024 · Vision-language and multimodal › Multimodal LLMs · approach: VLM capability analysis · 16 citations (OpenAlex)

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 mean-teacher pseudo-labels from unlabeled real images (ablation)supervised MSBDN · real adverse weather overallMUSIQ: 53.41 -> 54.08Improved
add VLM-based image assessment to select pseudo-labels (ablation)semi-supervised MSBDN · real adverse weather overallMUSIQ: 54.08 -> 56.68Improved
add pseudo-label initialization from existing restoration methods (ablation)semi-supervised MSBDN · real adverse weather overallMUSIQ: 56.68 -> 57.34Improved
add pseudo-label initialization (ablation)semi-supervised MSBDN · real adverse weather overallCLIP-IQA: 0.429 -> 0.425No clear effect
add weather prompt learning (CLIP prompts for clear vs weather) (ablation)semi-supervised MSBDN · real adverse weather overallMUSIQ: 57.34 -> 58.13Improved
add description-assisted semantics regularization (ablation)semi-supervised MSBDN · real adverse weather overallMUSIQ: 58.13 -> 58.91Improved
add iterative update of pseudo-labels (ablation)semi-supervised MSBDN · real adverse weather overallMUSIQ: 58.91 -> 59.34Improved
select pseudo-labels with VLM rating instead of NIMA, MUSIQ, CLIP-IQA or LIQE (ablation)semi-supervised MSBDN · real adverse weathervisual quality of restorationImproved
train with unlabeled real images and VLM guidance versus synthetic-only restoration baselinesadverse weather image restoration · real adverse weather overallMUSIQ: 56.38 -> 59.34Improved
use proposed method versus PromptIR on real haze imagesadverse weather image restoration · real hazeCLIP-IQA: 0.372 vs 0.371No clear effect

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