DeepAI AI Chat
Log In Sign Up

Semantically Contrastive Learning for Low-light Image Enhancement

by   Dong Liang, et al.
Nanjing University of Aeronautics and Astronautics
University of Leicester
Vivo Communication Technology Co. Ltd.
Nanyang Technological University

Low-light image enhancement (LLE) remains challenging due to the unfavorable prevailing low-contrast and weak-visibility problems of single RGB images. In this paper, we respond to the intriguing learning-related question – if leveraging both accessible unpaired over/underexposed images and high-level semantic guidance, can improve the performance of cutting-edge LLE models? Here, we propose an effective semantically contrastive learning paradigm for LLE (namely SCL-LLE). Beyond the existing LLE wisdom, it casts the image enhancement task as multi-task joint learning, where LLE is converted into three constraints of contrastive learning, semantic brightness consistency, and feature preservation for simultaneously ensuring the exposure, texture, and color consistency. SCL-LLE allows the LLE model to learn from unpaired positives (normal-light)/negatives (over/underexposed), and enables it to interact with the scene semantics to regularize the image enhancement network, yet the interaction of high-level semantic knowledge and the low-level signal prior is seldom investigated in previous methods. Training on readily available open data, extensive experiments demonstrate that our method surpasses the state-of-the-arts LLE models over six independent cross-scenes datasets. Moreover, SCL-LLE's potential to benefit the downstream semantic segmentation under extremely dark conditions is discussed. Source Code:


page 1

page 3

page 5

page 7


R2RNet: Low-light Image Enhancement via Real-low to Real-normal Network

Images captured in weak illumination conditions will seriously degrade t...

Learning Semantic-Aware Knowledge Guidance for Low-Light Image Enhancement

Low-light image enhancement (LLIE) investigates how to improve illuminat...

Contrastive Semantic-Guided Image Smoothing Network

Image smoothing is a fundamental low-level vision task that aims to pres...

Contrastive Monotonic Pixel-Level Modulation

Continuous one-to-many mapping is a less investigated yet important task...

Low-Light Image Enhancement by Learning Contrastive Representations in Spatial and Frequency Domains

Images taken under low-light conditions tend to suffer from poor visibil...

Learning with Nested Scene Modeling and Cooperative Architecture Search for Low-Light Vision

Images captured from low-light scenes often suffer from severe degradati...