.png){kind=icon}
Return
High-speed versatile video coding with memory-centered motion estimation and deep accelerator based coding unit partition
.png){kind=icon}
PRE
AI
DOI：10.1016/j.image.2026.117674.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• To develop an innovative Memory-Centered Motion Estimation with a deep accelerator-based CU Partition.
• To forecast the QTMT-based CU partition and avoid the majority of redundant processes during the rate-distortion optimization (RDO) search, an Adaptive Winograd Coding Unit Partitioning (AW-CUP) Accelerator is utilized.
• To improve the speed of SAD computations, the Hierarchical Carry Select Adder (HCSA) is used.
Keywords:
Versatile video coding
Motion estimation
Coding unit
Sum of absolute differences
Adaptive Winograd coding unit partitioning
Quad-tree multi-type tree
Rate-distortion optimization
And hierarchical carry select adder
Journal
S
IF:
2.7
Papers:
135
Citations:
0
Organization
View more organizations
Cited Papers
No cited papers available