.png){kind=icon}
.png){kind=icon}
Return
PAVEN: A Perceptual Algorithm for Versatile video Encoding using Neural networks
.png){kind=icon}
OA
AI
DOI：10.1016/j.engappai.2025.111664.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• A novel use of a neural network for saliency detection in YUV colorspace is proposed. • Trained network outperforms the original for its original purpose. • The proposed PAVEN algorithm selects frmae compression levels dynamically. • PAVEN reduces VVC bit rate by 7% with no perceptible quality loss for viewers.
Keywords:
Neural networks
Perceptual coding
Video coding
Versatile video coding
Subjective quality
Journal
IF:
8
Papers:
5.3K
Citations:
3.5W
Organization
No organization information available