GLARE: Low Light Image Enhancement Via Generative Latent Feature Based Codebook Retrieval

Abstract

Most existing Low-light Image Enhancement (LLIE) methods either directly map Low-Light (LL) to Normal-Light (NL) images or use semantic or illumination maps as guides. However, the ill-posed nature of LLIE and the difficulty of semantic retrieval from impaired inputs limit these methods, especially in extremely low-light conditions. To address this issue, we present a new LLIE network via Generative LAtent feature based codebook REtrieval (GLARE), in which the codebook prior is derived from undegraded NL images using a Vector Quantization (VQ) strategy. More importantly, we develop a generative Invertible Latent Normalizing Flow (I-LNF) module to align the LL feature distribution to NL latent representations, guaranteeing the correct code retrieval in the codebook. In addition, a novel Adaptive Feature Transformation (AFT) module, featuring an adjustable function for users and comprising an Adaptive Mix-up Block (AMB) along with a dual-decoder architecture, is devised to further enhanc

Stats

• citations40
• S2 citations—
• github stars136
• HF likes0
• heat score16.37
• arxiv keyzhou2024glare

Related papers

• Language Guided Local Infiltration For Interactive Image Retrieval (2023)5.24
• ELIP: Enhanced Visual-language Foundation Models For Image Retrieval (2025)2.26
• LLC: Accurate, Multi-purpose Learnt Low-dimensional Binary Codes (2021)2.29
• Give: Guiding Visual Encoder To Perceive Overlooked Information (2024)0.00
• Improving Nighttime Retrieval-based Localization (2018)0.00
• FLAIR: VLM With Fine-grained Language-informed Image Representations (2024)10.14
• Dark Side Augmentation: Generating Diverse Night Examples For Metric Learning (2023)8.34
• Optimized Feature Space Learning For Generating Efficient Binary Codes For Image Retrieval (2020)5.24