Saved in:
Bibliographic Details
Main Authors: Kim, Youngrae, Cho, Younggeol, Nguyen, Thanh-Tung, Hong, Seunghoon, Lee, Dongman
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2308.14334
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929417874309120
author Kim, Youngrae
Cho, Younggeol
Nguyen, Thanh-Tung
Hong, Seunghoon
Lee, Dongman
author_facet Kim, Youngrae
Cho, Younggeol
Nguyen, Thanh-Tung
Hong, Seunghoon
Lee, Dongman
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2308_14334
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle MetaWeather: Few-Shot Weather-Degraded Image Restoration
Kim, Youngrae
Cho, Younggeol
Nguyen, Thanh-Tung
Hong, Seunghoon
Lee, Dongman
Computer Vision and Pattern Recognition
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.
title MetaWeather: Few-Shot Weather-Degraded Image Restoration
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2308.14334