RDONet: Rate-Distortion Optimized Learned Image Compression With Variable Depth

Fabian Brand, Kristian Fischer, Alexander Kopte, Marc Windsheimer, André Kaup; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2022, pp. 1759-1763

Abstract

Rate-distortion optimization (RDO) is responsible for large gains in image and video compression. While RDO is a standard tool in traditional image and video coding, it is not yet widely used in novel end-to-end trained neural methods. The major reason is that the decoding function is trained once and does not have free parameters. In this paper, we present RDONet, a network containing state-of-the-art components, which is perceptually optimized and capable of rate-distortion optimization. With this network, we are able to outperform VVC Intra on MS-SSIM and two different perceptual LPIPS metrics. This paper is part of the CLIC challenge, where we participate under the team name RDONet_FAU.

Related Material

[pdf]
[bibtex]
@InProceedings{Brand_2022_CVPR, author = {Brand, Fabian and Fischer, Kristian and Kopte, Alexander and Windsheimer, Marc and Kaup, Andr\'e}, title = {RDONet: Rate-Distortion Optimized Learned Image Compression With Variable Depth}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2022}, pages = {1759-1763} }