TY  - CONF
AU  - Zhaocheng Liu
AU  - Luis Herranz
AU  - Fei Yang
AU  - Saiping Zhang
AU  - Shuai Wan
AU  - Marta Mrak
AU  - Marc Gorriz
A2  - CVPRW
PY  - 2022//
TI  - Slimmable Video Codec
BT  - CVPR 2022 Workshop and Challenge on Learned Image Compression (CLIC 2022, 5th Edition)
SP  - 1742
EP  - 1746
N2  - Neural video compression has emerged as a novel paradigm combining trainable multilayer neural net-works 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.
UR  - https://ieeexplore.ieee.org/document/9857273
L1  - http://refbase.cvc.uab.es/files/LHY2022.pdf
UR  - http://dx.doi.org/10.1109/CVPRW56347.2022.00183
N1  - MACO; 601.379; 601.161
ID  - Zhaocheng Liu2022
ER  -