TY - JOUR
T1 - Bi-Directional Deep Contextual Video Compression
AU - Sheng, Xihua
AU - Li, Li
AU - Liu, Dong
AU - Wang, Shiqi
PY - 2025/2/18
Y1 - 2025/2/18
N2 - Deep video compression has made impressive process in recent years, with the majority of advancements concentrated on P-frame coding. Although efforts to enhance B-frame coding are ongoing, their compression performance is still far behind that of traditional bi-directional video codecs. In this paper, we introduce a bi-directional deep contextual video compression scheme tailored for B-frames, termed DCVC-B, to improve the compression performance of deep B-frame coding. Our scheme mainly has three key innovations. First, we develop a bi-directional motion difference context propagation method for effective motion difference coding, which significantly reduces the bit cost of bi-directional motions. Second, we propose a bi-directional contextual compression model and a corresponding bi-directional temporal entropy model, to make better use of the multi-scale temporal contexts. Third, we propose a hierarchical quality structure-based training strategy, leading to an effective bit allocation across large groups of pictures (GOP). Experimental results show that our DCVC-B achieves an average reduction of 26.6% in BD-Rate compared to the reference software for H.265/HEVC under random access conditions. Remarkably, it surpasses the performance of the H.266/VVC reference software on certain test datasets under the same configuration. We anticipate our work can provide valuable insights and bring up deep B-frame coding to the next level. © 2025 IEEE.
AB - Deep video compression has made impressive process in recent years, with the majority of advancements concentrated on P-frame coding. Although efforts to enhance B-frame coding are ongoing, their compression performance is still far behind that of traditional bi-directional video codecs. In this paper, we introduce a bi-directional deep contextual video compression scheme tailored for B-frames, termed DCVC-B, to improve the compression performance of deep B-frame coding. Our scheme mainly has three key innovations. First, we develop a bi-directional motion difference context propagation method for effective motion difference coding, which significantly reduces the bit cost of bi-directional motions. Second, we propose a bi-directional contextual compression model and a corresponding bi-directional temporal entropy model, to make better use of the multi-scale temporal contexts. Third, we propose a hierarchical quality structure-based training strategy, leading to an effective bit allocation across large groups of pictures (GOP). Experimental results show that our DCVC-B achieves an average reduction of 26.6% in BD-Rate compared to the reference software for H.265/HEVC under random access conditions. Remarkably, it surpasses the performance of the H.266/VVC reference software on certain test datasets under the same configuration. We anticipate our work can provide valuable insights and bring up deep B-frame coding to the next level. © 2025 IEEE.
KW - Bi-Directional Contextual Compression
KW - Bi-Directional Motion Compression
KW - Bi-Directional Temporal Context Mining
KW - Deep B-Frame Compression
KW - Hierarchical Quality Structure
UR - http://www.scopus.com/inward/record.url?scp=85218737478&partnerID=8YFLogxK
UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-85218737478&origin=recordpage
U2 - 10.1109/TMM.2025.3543061
DO - 10.1109/TMM.2025.3543061
M3 - RGC 21 - Publication in refereed journal
SN - 1520-9210
JO - IEEE Transactions on Multimedia
JF - IEEE Transactions on Multimedia
ER -