在线时间:8:00-16:00
迪恩网络APP
随时随地掌握行业动态
扫描二维码
关注迪恩网络微信公众号
开源软件名称:Deep-Painterly-Harmonization开源软件地址:https://gitee.com/mirrors/Deep-Painterly-Harmonization开源软件介绍:deep-painterly-harmonizationCode and data for paper "Deep Painterly Harmonization" DisclaimerThis software is published for academic and non-commercial use only. SetupThis code is based on torch. It has been tested on Ubuntu 16.04 LTS. Dependencies: CUDA backend: Download VGG-19: sh models/download_models.sh Compile make clean && make UsageTo generate all results (in python gen_all.py in Python and then run('filt_cnn_artifact.m') in Matlab or Octave. The final output will be in Note that in the paper we trained a CNN on a dataset of 80,000 paintings collected from wikiart.org, which estimates the stylization level of a given painting and adjust weights accordingly. We will release the pre-trained model in the next update. Users will need to set those weights manually if running on their new paintings for now. Removed a few images due to copyright issue. Full set here for testing use only. ExamplesHere are some results from our algorithm (from left to right are original painting, naive composite and our output):
Acknowledgement
CitationIf you find this work useful for your research, please cite: @article{luan2018deep, title={Deep Painterly Harmonization}, author={Luan, Fujun and Paris, Sylvain and Shechtman, Eli and Bala, Kavita}, journal={arXiv preprint arXiv:1804.03189}, year={2018}} ContactFeel free to contact me if there is any question (Fujun Luan [email protected]). |
请发表评论