Salvato in:
Dettagli Bibliografici
Autori principali: Dong, Wei, Min, Yan, Zhou, Han, Chen, Jun
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2504.14075
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915250184388608
author Dong, Wei
Min, Yan
Zhou, Han
Chen, Jun
author_facet Dong, Wei
Min, Yan
Zhou, Han
Chen, Jun
contents Current Low-light Image Enhancement (LLIE) techniques predominantly rely on either direct Low-Light (LL) to Normal-Light (NL) mappings or guidance from semantic features or illumination maps. Nonetheless, the intrinsic ill-posedness of LLIE and the difficulty in retrieving robust semantics from heavily corrupted images hinder their effectiveness in extremely low-light environments. To tackle this challenge, we present SG-LLIE, a new multi-scale CNN-Transformer hybrid framework guided by structure priors. Different from employing pre-trained models for the extraction of semantics or illumination maps, we choose to extract robust structure priors based on illumination-invariant edge detectors. Moreover, we develop a CNN-Transformer Hybrid Structure-Guided Feature Extractor (HSGFE) module at each scale with in the UNet encoder-decoder architecture. Besides the CNN blocks which excels in multi-scale feature extraction and fusion, we introduce a Structure-Guided Transformer Block (SGTB) in each HSGFE that incorporates structural priors to modulate the enhancement process. Extensive experiments show that our method achieves state-of-the-art performance on several LLIE benchmarks in both quantitative metrics and visual quality. Our solution ranks second in the NTIRE 2025 Low-Light Enhancement Challenge. Code is released at https://github.com/minyan8/imagine.
format Preprint
id arxiv_https___arxiv_org_abs_2504_14075
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Towards Scale-Aware Low-Light Enhancement via Structure-Guided Transformer Design
Dong, Wei
Min, Yan
Zhou, Han
Chen, Jun
Computer Vision and Pattern Recognition
Current Low-light Image Enhancement (LLIE) techniques predominantly rely on either direct Low-Light (LL) to Normal-Light (NL) mappings or guidance from semantic features or illumination maps. Nonetheless, the intrinsic ill-posedness of LLIE and the difficulty in retrieving robust semantics from heavily corrupted images hinder their effectiveness in extremely low-light environments. To tackle this challenge, we present SG-LLIE, a new multi-scale CNN-Transformer hybrid framework guided by structure priors. Different from employing pre-trained models for the extraction of semantics or illumination maps, we choose to extract robust structure priors based on illumination-invariant edge detectors. Moreover, we develop a CNN-Transformer Hybrid Structure-Guided Feature Extractor (HSGFE) module at each scale with in the UNet encoder-decoder architecture. Besides the CNN blocks which excels in multi-scale feature extraction and fusion, we introduce a Structure-Guided Transformer Block (SGTB) in each HSGFE that incorporates structural priors to modulate the enhancement process. Extensive experiments show that our method achieves state-of-the-art performance on several LLIE benchmarks in both quantitative metrics and visual quality. Our solution ranks second in the NTIRE 2025 Low-Light Enhancement Challenge. Code is released at https://github.com/minyan8/imagine.
title Towards Scale-Aware Low-Light Enhancement via Structure-Guided Transformer Design
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2504.14075