WACV 2021論文 | 愛奇藝提出，僅需一幀顏色圖即可完成線稿自動著色

程式設計師回湘發表於2020-12-14

 

相關性矩陣的計算：

 

圖二. CMFT計算過程

圖三. 網路結構概覽

圖四. 網路結構

 

 

參考文獻：

[1] https://arxiv.org/pdf/2004.06718.pdf

[2] Liao, Jing, et al. "Visual attribute transfer through deep image analogy." arXiv preprint arXiv:1705.01088 (2017).

[3]  Aaron Hertzmann, Charles E Jacobs, Nuria Oliver, Brian Curless, and David H Salesin. Image analogies. In Proceedings of the 28th annual conference on Computer graphics and interactive techniques, pages 327–340, 2001.

[4] Harrish Thasarathan, Kamyar Nazeri, and Mehran Ebrahimi. Automatic temporally coherent video colorization. In 2019 16th Conference on Computer and Robot Vision (CRV), pages 189–194. IEEE, 2019

[5] Phillip Isola, Jun-Yan Zhu, Tinghui Zhou, and Alexei A Efros. Image-to-image translation with conditional adversarial networks. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 1125–1134, 2017.

[6] http://vr.sina.com.cn/news/hz/2020-11-16/doc-iiznezxs2137644.shtml

 

相關文章