Neural video compression has emerged as a novel paradigm combining trainable multilayer neural networks and machine learning, achieving competitive rate-distortion (RD) performances, but still remaining impractical due to heavy neural architectures, with large memory and computational demands. In addition, models are usually optimized for a single RD tradeoff. Recent slimmable image codecs can dynamically adjust their model capacity to gracefully reduce the memory and computation requirements, without harming RD performance. In this paper we propose a slimmable video codec (SlimVC), by integrating a slimmable temporal entropy model in a slimmable autoencoder. Despite a significantly more complex architecture, we show that slimming remains a powerful mechanism to control rate, memory footprint, computational cost and latency, all being important requirements for practical video compression.
@article{arxiv.2205.06754,
title = {Slimmable Video Codec},
author = {Zhaocheng Liu and Luis Herranz and Fei Yang and Saiping Zhang and Shuai Wan and Marta Mrak and Marc Górriz Blanch},
journal= {arXiv preprint arXiv:2205.06754},
year = {2022}
}
Comments
Computer Vision and Pattern Recognition Workshop(CLIC2022)