@inproceedings{329ebb113f6f4f5687261b333401b010,
title = "Learning-Based Scalable Video Coding with Spatial and Temporal Prediction",
abstract = "In this work, we propose a hybrid learning-based method for layered spatial scalability. Our framework consists of a base layer (BL), which encodes a spatially downsampled representation of the input video using Versatile Video Coding (VVC), and a learning-based enhancement layer (EL), which conditionally encodes the original video signal. The EL is conditioned by two fused prediction signals: A spatial inter-layer prediction signal, that is generated by spatially upsampling the output of the BL using super-resolution, and a temporal inter-frame prediction signal, that is generated by decoder-side motion compensation without signaling any motion vectors. We show that our method outperforms LCEVC and has comparable performance to full-resolution VVC for high-resolution content, while still offering scalability.",
keywords = "conditional coding, scalable coding, spatial scalability, video coding, VVC",
author = "Martin Benjak and Chen, {Yi Hsin} and Peng, {Wen Hsiao} and Jorn Ostermann",
note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 2023 IEEE International Conference on Visual Communications and Image Processing, VCIP 2023 ; Conference date: 04-12-2023 Through 07-12-2023",
year = "2023",
doi = "10.1109/VCIP59821.2023.10402677",
language = "English",
series = "2023 IEEE International Conference on Visual Communications and Image Processing, VCIP 2023",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
booktitle = "2023 IEEE International Conference on Visual Communications and Image Processing, VCIP 2023",
address = "United States",
}