Codec-Simulation Network for Joint Optimization of Video Coding With Pre- and Post-Processing
Year: 2021
Type: article
Abstract: In real video coding systems, there might be pre-processing before the encoding and post-processing after the decoding. Those pre- and post-processing should be jointly optimized considering the existing of distortions introduced by lossy coding in between. This paper proposes a differentiable network to simulate the non-differentiable traditional coding to make the joint optimization of pre- and post-processing possible. The proposed codec-simulation network can achieve up to 49.4dB simulation accuracy for HEVC codec in intra mode. When we use down-sampling and up-sampling as examples of pre- and post-processing of a video codec, the joint optimization of these two processing modules in a video coding system can result in 46.88% and 55.15% BD-rate reduction based on PSNR and SSIM compared with that without joint optimization.
Authors: Kaitian Qiu, Lu Yu, Daowen Li
Institution: Zhejiang University
Language: English
Subfield: Signal Processing
Field: Computer Science
Domain: Physical Sciences
Open Access status: gold
Estimated APC paid: $1,750
Award: G8748308789
OpenAlex ID: W3214878703
