Scribble-to-Painting Transformation with Multi-Task Generative Adversarial Networks

Authors: Jinning Li, Yexiang Xue

IJCAI 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experimental result shows that DSP-Net outperforms state-of-the-art models both visually and quantitatively.
Researcher Affiliation Academia Jinning Li1 and Yexiang Xue2 1Shanghai Jiao Tong University 2Purdue University lijinning@sjtu.edu.cn, yexiang@purdue.edu
Pseudocode No The paper describes the network architecture and mathematical objectives, but does not include any pseudocode or algorithm blocks.
Open Source Code Yes The code and dataset could be found at https://github.com/jinningli/DSP-Net.
Open Datasets Yes In this paper, we build a triple dataset including scribbles, paintings and semantic images based on COCO dataset [Lin et al., 2014].
Dataset Splits No We split the dataset into 4500 images for training and 500 images for a test.
Hardware Specification No The paper does not specify the hardware used for running the experiments (e.g., GPU models, CPU types, or cloud resources).
Software Dependencies No The paper mentions various models and algorithms used (e.g., VGG19 network, Pix2pix, Cycle GAN), but it does not specify software dependencies with version numbers (e.g., Python, PyTorch, TensorFlow versions).
Experiment Setup Yes We train the GAN based models for 200 epochs and neural style for 1000 iterations. We keep the other hyper-parameters and basic settings as the recommended value mentioned in their original code.