Sorry, you need to enable JavaScript to visit this website.

Deep Video Compression for Interframe Coding

Citation Author(s):
David Alexandre, Hsueh-Ming Hang, Wen-Hsiao Peng, Marek Domański
Submitted by:
David Alexandre
Last updated:
28 September 2021 - 3:57am
Document Type:
Presentation Slides
Document Year:
2021
Event:
Presenters Name:
David Alexandre
Categories:

Abstract 

Abstract: 

A typical learning-based video compression scheme consists of motion coding and residual coding. In this paper, our deep video compression features a motion predictor and a refinement networks for interframe coding. To save the bits for transmitting motion information, our scheme performs local motion prediction and sends only the differential motion vectors to the decoder. In the residual coding, we couple the residual decoder with the refine-net to reduce residual signal bits. The experiments show that our work can achieve a higher coding performance compared to the known learningbased video codecs.

up
0 users have voted:

Dataset Files

DEEP VIDEO COMPRESSION FOR INTERFRAME CODING - ICIP 2021 - Presentation Day.pdf

(14)