Dataset for IJCAI 2019 paper, Scribble-to-Painting Transformation with Multi-Task Generative Adversarial Networks
| Main Authors: | Jinning Li, Yexiang Xue |
|---|---|
| Format: | info dataset |
| Terbitan: |
, 2019
|
| Subjects: | |
| Online Access: |
https://zenodo.org/record/3417898 |
Daftar Isi:
- The dataset and pre-trained model for IJCAI 2019 paper "Scribble-to-Painting Transformation with Multi-Task Generative Adversarial Networks" Pre-trained model(Pytorch): DSPNet_G_200_epochs.pth Dataset (generated from coco dataset): starry_night_coco.zip Github: https://github.com/jinningli/DSP-Net Please cite our paper if you are using this dataset: Jinning Li, and Yexiang Xue. Scribble-to-Painting Transformation with Multi-Task Generative Adversarial Networks. In International Joint Conference on Artificial Intelligence (IJCAI) 2019 Abstract: We propose the Dual Scribble-to-Painting Network (DSP-Net), which is able to produce artistic paintings based on user-generated scribbles. In scribble-to-painting transformation, a neural net has to infer additional details of the image, given relatively sparse information contained in the outlines of the scribble. Therefore, it is more challenging than classical image style transfer, in which the information content is reduced from photos to paintings. Inspired by the human cognitive process, we propose a multi-task generative adversarial network, which consists of two jointly trained neural nets -- one for generating artistic images and the other one for semantic segmentation. We demonstrate that joint training on these two tasks brings in additional benefit. Experimental result shows that DSP-Net outperforms state-of-the-art models both visually and quantitatively. In addition, we publish a large dataset for scribble-to-painting transformation.