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

TL;DR

BINet introduces a binary inpainting autoencoder that enhances patch-based image compression by maintaining inter-patch dependencies, reducing block artefacts, and enabling parallel encoding and decoding.

Contribution

This paper presents BINet, a novel autoencoder framework that uses binary inpainting to improve patch-based image compression by preserving inter-patch relationships.

Findings

Improves compression quality across various levels.

Reduces block artefacts at low bitrates.

Enables parallel encoding and decoding.

Abstract

Recent deep learning models outperform standard lossy image compression codecs. However, applying these models on a patch-by-patch basis requires that each image patch be encoded and decoded independently. The influence from adjacent patches is therefore lost, leading to block artefacts at low bitrates. We propose the Binary Inpainting Network (BINet), an autoencoder framework which incorporates binary inpainting to reinstate interdependencies between adjacent patches, for improved patch-based compression of still images. When decoding a patch, BINet additionally uses the binarised encodings from surrounding patches to guide its reconstruction. In contrast to sequential inpainting methods where patches are decoded based on previons reconstructions, BINet operates directly on the binary codes of surrounding patches without access to the original or reconstructed image data. Encoding and decoding can therefore be performed in parallel. We demonstrate that BINet improves the compression quality of a competitive deep image codec across a range of compression levels.