Saved in:
Bibliographic Details
Main Authors: Kirillov, Ivan, Parkhomenko, Denis, Chernyshev, Kirill, Pletnev, Alexander, Shi, Yibo, Lin, Kai, Babin, Dmitry
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2406.16544
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911930599342080
author Kirillov, Ivan
Parkhomenko, Denis
Chernyshev, Kirill
Pletnev, Alexander
Shi, Yibo
Lin, Kai
Babin, Dmitry
author_facet Kirillov, Ivan
Parkhomenko, Denis
Chernyshev, Kirill
Pletnev, Alexander
Shi, Yibo
Lin, Kai
Babin, Dmitry
contents Learned video compression methods already outperform VVC in the low-delay (LD) case, but the random-access (RA) scenario remains challenging. Most works on learned RA video compression either use HEVC as an anchor or compare it to VVC in specific test conditions, using RGB-PSNR metric instead of Y-PSNR and avoiding comprehensive evaluation. Here, we present an end-to-end learned video codec for random access that combines training on long sequences of frames, rate allocation designed for hierarchical coding and content adaptation on inference. We show that under common test conditions (JVET-CTC), it achieves results comparable to VTM (VVC reference software) in terms of YUV-PSNR BD-Rate on some classes of videos, and outperforms it on almost all test sets in terms of VMAF BD-Rate. On average it surpasses open LD and RA end-to-end solutions in terms of VMAF and YUV BD-Rates.
format Preprint
id arxiv_https___arxiv_org_abs_2406_16544
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Hierarchical B-frame Video Coding for Long Group of Pictures
Kirillov, Ivan
Parkhomenko, Denis
Chernyshev, Kirill
Pletnev, Alexander
Shi, Yibo
Lin, Kai
Babin, Dmitry
Computer Vision and Pattern Recognition
Learned video compression methods already outperform VVC in the low-delay (LD) case, but the random-access (RA) scenario remains challenging. Most works on learned RA video compression either use HEVC as an anchor or compare it to VVC in specific test conditions, using RGB-PSNR metric instead of Y-PSNR and avoiding comprehensive evaluation. Here, we present an end-to-end learned video codec for random access that combines training on long sequences of frames, rate allocation designed for hierarchical coding and content adaptation on inference. We show that under common test conditions (JVET-CTC), it achieves results comparable to VTM (VVC reference software) in terms of YUV-PSNR BD-Rate on some classes of videos, and outperforms it on almost all test sets in terms of VMAF BD-Rate. On average it surpasses open LD and RA end-to-end solutions in terms of VMAF and YUV BD-Rates.
title Hierarchical B-frame Video Coding for Long Group of Pictures
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2406.16544