All-weather Multi-Modality Image Fusion: Unified Framework and 100k Benchmark

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Li, Xilai, Liu, Wuyang, Li, Xiaosong, Zhou, Fuqiang, Li, Huafeng, Nie, Feiping
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866915860160970752
author Li, Xilai
Liu, Wuyang
Li, Xiaosong
Zhou, Fuqiang
Li, Huafeng
Nie, Feiping
author_facet Li, Xilai
Liu, Wuyang
Li, Xiaosong
Zhou, Fuqiang
Li, Huafeng
Nie, Feiping
contents Multi-modality image fusion (MMIF) combines complementary information from different image modalities to provide a comprehensive and objective interpretation of scenes. However, existing fusion methods cannot resist different weather interferences in real-world scenes, limiting their practical applicability. To bridge this gap, we propose an end-to-end, unified all-weather MMIF model. Rather than focusing solely on pixel-level recovery, our method emphasizes maximizing the representation of key scene information through joint feature fusion and restoration. Specifically, we first decompose images into low-rank and sparse components, enabling effective feature separation for enhanced multi-modality perception. During feature recovery, we introduce a physically-aware clear feature prediction module, inferring variations in light transmission via illumination and reflectance. Clear features generated by the network are used to enhance salient information representation. We also construct a large-scale MMIF dataset with 100,000 image pairs comprehensively across rain, haze, and snow conditions, as well as covering various degradation levels and diverse scenes. Experimental results in both real-world and synthetic scenes demonstrate that the proposed method excels in image fusion and downstream tasks such as object detection, semantic segmentation, and depth estimation. The code is available at https://github.com/ixilai/AWFusion.
format Preprint
id arxiv_https___arxiv_org_abs_2402_02090
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle All-weather Multi-Modality Image Fusion: Unified Framework and 100k Benchmark
Li, Xilai
Liu, Wuyang
Li, Xiaosong
Zhou, Fuqiang
Li, Huafeng
Nie, Feiping
Computer Vision and Pattern Recognition
Multi-modality image fusion (MMIF) combines complementary information from different image modalities to provide a comprehensive and objective interpretation of scenes. However, existing fusion methods cannot resist different weather interferences in real-world scenes, limiting their practical applicability. To bridge this gap, we propose an end-to-end, unified all-weather MMIF model. Rather than focusing solely on pixel-level recovery, our method emphasizes maximizing the representation of key scene information through joint feature fusion and restoration. Specifically, we first decompose images into low-rank and sparse components, enabling effective feature separation for enhanced multi-modality perception. During feature recovery, we introduce a physically-aware clear feature prediction module, inferring variations in light transmission via illumination and reflectance. Clear features generated by the network are used to enhance salient information representation. We also construct a large-scale MMIF dataset with 100,000 image pairs comprehensively across rain, haze, and snow conditions, as well as covering various degradation levels and diverse scenes. Experimental results in both real-world and synthetic scenes demonstrate that the proposed method excels in image fusion and downstream tasks such as object detection, semantic segmentation, and depth estimation. The code is available at https://github.com/ixilai/AWFusion.
title All-weather Multi-Modality Image Fusion: Unified Framework and 100k Benchmark
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2402.02090