Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in Coakley et alK. L. Coakley, T. Snelleman, H. Hoos, and O. E. Gundersen, "The embrace of open science: An analysis of a decade of AI research and 56 800 conference papers," Under Review, 2026..
Synergistic Multiscale Detail Refinement via Intrinsic Supervision for Underwater Image Enhancement
Authors: Dehuan Zhang, Jingchun Zhou, Chunle Guo, Weishi Zhang, Chongyi Li
AAAI 2024 | Venue PDF | 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. |