Synergistic Multiscale Detail Refinement via Intrinsic Supervision for Underwater Image Enhancement

Authors: Dehuan Zhang, Jingchun Zhou, Chunle Guo, Weishi Zhang, Chongyi Li

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

Reproducibility Variable Result LLM Response
Research Type Experimental Experiments Datasets, Implementation Details, Comparison Results, Ablation Study
Researcher Affiliation Academia 1 College of Information Science and Technology, Dalian Maritime University 2 VCIP, CS, Nankai University
Pseudocode No The paper does not contain structured pseudocode or algorithm blocks.
Open Source Code Yes The code is publicly available at: https: //github.com/zhoujingchun03/SMDR-IS
Open Datasets Yes We trained SMDR-IS utilizing the UIEB dataset, which consists of 800 training images and 90 paired testing images. To assess the robustness of SMDR-IS, we further conducted the evaluation on various datasets, i.e. UIEB, U45, LSUI. Li et al. 2019. An Underwater Image Enhancement Benchmark Dataset and Beyond. IEEE Transactions on Image Processing, 29: 4376 4389.
Dataset Splits No The paper mentions 800 training images and 90 paired testing images for the UIEB dataset but does not explicitly detail a validation split or its size.
Hardware Specification Yes Our method was implemented using Py Torch, with an NVIDIA Tesla V100 GPU, Intel(R) Xeon(R) Silver 4114 CPU, and 32GB RAM.
Software Dependencies No The paper mentions "PyTorch" but does not specify its version or any other software dependencies with version numbers.
Experiment Setup Yes For training, images were randomly cropped to a resolution of 256 x 256, and we used a batch size of 44 and a learning rate of 0.0002.