DehazeGAN: When Image Dehazing Meets Differential Programming

Authors: Hongyuan Zhu, Xi Peng, Vijay Chandrasekhar, Liyuan Li, Joo-Hwee Lim

IJCAI 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments on synthetic and realistic data show that our method outperforms state-of-the-art methods in terms of PSNR, SSIM, and subjective visual quality.
Researcher Affiliation Academia Hongyuan Zhu1, Xi Peng2 , Vijay Chandrasekhar1, Liyuan Li1, Joo-Hwee Lim1 1 Institute for Infocomm Research, A*STAR, Singapore 2 College of Computer Science, Sichuan University, China {zhuh, vijay, lyli, joohwee}@i2r.a-star.edu.sg, pangsaai@gmail.com
Pseudocode No No explicit pseudocode or algorithm blocks were found in the paper.
Open Source Code No No explicit statement about providing open-source code or a link to a repository was found.
Open Datasets Yes The dataset is synthesized using the indoor images from the SUN-RGBD dataset [Song et al., 2015], NYU-Depth dataset [Silberman et al., 2012] and natural images from the COCO dataset [Lin et al., 2014].
Dataset Splits Yes After generating the hazy images, we randomly choose 85% data for training, 10% data for validation, and a small number of test images to form the indoor and outdoor subsets.
Hardware Specification Yes The entire network is trained on a Nvidia Titan X GPU in PyTorch.
Software Dependencies No The paper mentions 'PyTorch' and 'ADAM' but does not specify their version numbers or any other software dependencies with versions.
Experiment Setup Yes For training, we employ the ADAM [Kingma and Ba, 2015] optimizer with a learning rate of 0.002 and a batch size of eight. We set γ = 10 4 through the cross-validation.