Unpaired Image Enhancement Featuring Reinforcement-Learning-Controlled Image Editing Software

Authors: Satoshi Kosugi, Toshihiko Yamasaki11296-11303

AAAI 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Our experimental results demonstrate that the proposed method achieves better performance, compared to the performances of the state-of-the-art methods based on unpaired learning.
Researcher Affiliation Academia Satoshi Kosugi, Toshihiko Yamasaki Department of Information and Communication Engineering, The University of Tokyo, Tokyo, Japan
Pseudocode No The paper does not contain any structured pseudocode or algorithm blocks.
Open Source Code No The paper does not include an unambiguous statement or a direct link indicating that the source code for the described methodology is publicly available.
Open Datasets Yes We use the MIT-Adobe 5K dataset (Bychkovsky et al. 2011) for training and testing. For training and testing, we use the SCUTFBP5500 dataset (Liang et al. 2018)
Dataset Splits No To create unpaired image sets, we use 2,250 original images and non-overlapping 2,250 retouched images as training data, and the other 500 pairs are used as test data. The paper specifies train and test splits, but does not provide specific details for a separate validation set split.
Hardware Specification No The paper does not provide specific details about the hardware used for running experiments, such as GPU or CPU models.
Software Dependencies No The paper mentions using Python to reproduce filters from Adobe Lightroom and Photoshop, and the Adam optimizer, but does not specify version numbers for any software dependencies.
Experiment Setup Yes We optimize the discriminator and the generator using Adam (Kingma and Ba 2014) with a learning rate of 10 4. Other parameters λ, α, β, L, and U are 10, 100, 0.001, 33, and 5, respectively. The hyperparameters are the same as those used for photo enhancement, except that α and L are 300 and 17, respectively.