SLLEN: Semantic-aware Low-light Image Enhancement Network

TL;DR

This paper introduces SLLEN, a semantic-aware low-light image enhancement network that effectively leverages intermediate and high-level semantic features through a shared encoder and alternating training, resulting in superior enhancement quality.

Contribution

The paper proposes a novel SLLEN framework that integrates intermediate and high-level semantic features via shared encoding and alternating training to improve low-light image enhancement.

Findings

SLLEN outperforms state-of-the-art methods in LLE quality.

The use of intermediate embedding features enhances enhancement performance.

Shared encoder and alternating training facilitate better semantic feature utilization.

Abstract

How to effectively explore semantic feature is vital for low-light image enhancement (LLE). Existing methods usually utilize the semantic feature that is only drawn from the output produced by high-level semantic segmentation (SS) network. However, if the output is not accurately estimated, it would affect the high-level semantic feature (HSF) extraction, which accordingly interferes with LLE. To this end, we develop a simple and effective semantic-aware LLE network (SSLEN) composed of a LLE main-network (LLEmN) and a SS auxiliary-network (SSaN). In SLLEN, LLEmN integrates the random intermediate embedding feature (IEF), i.e., the information extracted from the intermediate layer of SSaN, together with the HSF into a unified framework for better LLE. SSaN is designed to act as a SS role to provide HSF and IEF. Moreover, thanks to a shared encoder between LLEmN and SSaN, we further propose an alternating training mechanism to facilitate the collaboration between them. Unlike currently available approaches, the proposed SLLEN is able to fully lever the semantic information, e.g., IEF, HSF, and SS dataset, to assist LLE, thereby leading to a more promising enhancement performance. Comparisons between the proposed SLLEN and other state-of-the-art techniques demonstrate the superiority of SLLEN with respect to LLE quality over all the comparable alternatives.