BINet: A binary inpainting network for deep patch-based image compression

作者：

Highlights：

• Binary inpainting for improved deep patch-based image compression.

• Full-context binary inpainting outperforms sequential inpainting techniques.

• BINet makes fully parallelizable inpainting possible within the context of image compression.

摘要

•Binary inpainting for improved deep patch-based image compression.•Full-context binary inpainting outperforms sequential inpainting techniques.•BINet makes fully parallelizable inpainting possible within the context of image compression.

论文关键词：Image compression,Image inpainting,Image representation coding,Deep compression

论文评审过程：Received 9 April 2020, Revised 6 November 2020, Accepted 16 December 2020, Available online 26 December 2020, Version of Record 28 December 2020.

论文官网地址：https://doi.org/10.1016/j.image.2020.116119