VQCNIR: Clearer Night Image Restoration with Vector-Quantized Codebook

Authors: Wenbin Zou, Hongxia Gao, Tian Ye, Liang Chen, Weipeng Yang, Shasha Huang, Hongsheng Chen, Sixiang Chen

AAAI 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments validate the remarkable benefits of VQCNIR in enhancing image quality under low-light conditions, showcasing its state-of-the-art performance on both synthetic and real-world datasets.
Researcher Affiliation Academia 1The School of Automation Science and Engineering, South China University of Technology, Guangzhou 2Research Center for Brain-Computer Interface, Pazhou Laboratory, Guangzhou 3The Hong Kong University of Science and Technology, Guangzhou 4College of Photonic and Electronic Engineering, Fujian Normal University, Fuzhou
Pseudocode No The paper does not contain any structured pseudocode or algorithm blocks.
Open Source Code Yes The code is available at https://github.com/Alex Zou14/VQCNIR.
Open Datasets Yes We train our VQCNIR network on the LOL-Blur dataset (2022)
Dataset Splits No We train our VQCNIR network on the LOL-Blur dataset (2022), which consists of 170 sequences (10,200 pairs) of training data and 30 sequences (1,800 pairs) of test data.
Hardware Specification Yes All experiments are performed on a PC equipped with Intel Core i7-13700K CPU, 32G RAM, and the Nvidia RTX 3090 GPU with CUDA 11.2.
Software Dependencies Yes CUDA 11.2
Experiment Setup Yes We train our network using Adam (2014) optimizer with β1=0.9, β2=0.99 for a total of 500k iterations. The mini-batch size is set to 8. The initial learning rate is set to 1 10 4 and adopts the Multi Step LR to adjust the learning rate progressively. We empirically set λpix, λca, λper, and λadv to {1, 1, 1, 0.1}.