Back to Search Document details
26th Meeting: by teleconference, April 2022 2022-04-20 23:10
EE1-1.7-related: Improved RDO Considering Deep In-Loop Filter and Deblocking
Authors: Jingxin Li ByteDance Yun Li ByteDance Kai Zhang ByteDance Li Zhang ByteDance
Abstract
This contribution presents an encoder optimization technique on top of the deep learning-based in-loop filtering method combined with deblocking in EE1-1.7. The proposed method is asserted to improve the compression efficiency at encoder by introducing CNN-based filtering and deblocking into the rate-distortion optimization (RDO) process. Compared with VTM11.0_nnvc, the proposed method reportedly shows on average {8.52%, 22.43%, 23.46%}, { x.xx %, x.xx %, x.xx %}, and {x%, x%, x%} BD-rate reductions for {Y, Cb, Cr} components, under AI, RA, and LDB configurations, respectively.
References:
JVET-X0084 JVET-X2016 JVET-Z0113
Cited:
JVET-AA0113 JVET-Z0011 JVET-Z0023
PATENTS:
US12542919B2 0.70 2026-02-03 WO2025072638A1 0.34 2025-04-03 WO2025072627A1 0.32 2025-04-03 TW202537274A 0.31 2025-09-16 WO2025085531A1 0.30 2025-04-24 US11218695B2 0.28 2022-01-04 TWI830107B 0.26 2024-01-21 US12445633B2 0.24 2025-10-14
ARCHIVE v2 :
JVET-Z0155.docx JVET-Z0155.pdf JVET-Z0155_r1.docx JVET_Z0155.xlsm JVET_Z0155_vs_EE1-1.7.xlsm
Citation