MetaWeather: Few-Shot Weather-Degraded Image Restoration

• URL: http://arxiv.org/abs/2308.14334v4
• Date: Fri, 12 Jul 2024 06:19:52 GMT
• Title: MetaWeather: Few-Shot Weather-Degraded Image Restoration
• Authors: Youngrae Kim, Younggeol Cho, Thanh-Tung Nguyen, Seunghoon Hong, Dongman Lee,
• Abstract summary: We introduce MetaWeather, a universal approach that can handle diverse and novel weather conditions with a single unified model. We show that MetaWeather can adapt to unseen weather conditions, significantly outperforming state-of-the-art multi-weather image restoration methods.
• Score: 17.63266150036311
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Real-world weather conditions are intricate and often occur concurrently. However, most existing restoration approaches are limited in their applicability to specific weather conditions in training data and struggle to generalize to unseen weather types, including real-world weather conditions. To address this issue, we introduce MetaWeather, a universal approach that can handle diverse and novel weather conditions with a single unified model. Extending a powerful meta-learning framework, MetaWeather formulates the task of weather-degraded image restoration as a few-shot adaptation problem that predicts the degradation pattern of a query image, and learns to adapt to unseen weather conditions through a novel spatial-channel matching algorithm. Experimental results on the BID Task II.A, SPA-Data, and RealSnow datasets demonstrate that the proposed method can adapt to unseen weather conditions, significantly outperforming the state-of-the-art multi-weather image restoration methods.

Related papers

Err

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.