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

Brand F, Fischer K, Kopte A, Windsheimer M, Kaup A (2022)


Publication Type: Conference contribution

Publication year: 2022

Publisher: IEEE Computer Society

Book Volume: 2022-June

Pages Range: 1758-1762

Conference Proceedings Title: IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops

Event location: New Orleans, LA, USA

ISBN: 9781665487399

DOI: 10.1109/CVPRW56347.2022.00186

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.

Authors with CRIS profile

How to cite

APA:

Brand, F., Fischer, K., Kopte, A., Windsheimer, M., & Kaup, A. (2022). RDONet: Rate-Distortion Optimized Learned Image Compression with Variable Depth. In IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (pp. 1758-1762). New Orleans, LA, USA: IEEE Computer Society.

MLA:

Brand, Fabian, et al. "RDONet: Rate-Distortion Optimized Learned Image Compression with Variable Depth." Proceedings of the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2022, New Orleans, LA, USA IEEE Computer Society, 2022. 1758-1762.

BibTeX: Download