2019
DOI: 10.1007/978-3-030-37731-1_9
|View full text |Cite
|
Sign up to set email alerts
|

Down-Sampling Based Video Coding with Degradation-Aware Restoration-Reconstruction Deep Neural Network

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
2
1

Citation Types

1
61
0

Year Published

2020
2020
2023
2023

Publication Types

Select...
5
1

Relationship

1
5

Authors

Journals

citations
Cited by 17 publications
(62 citation statements)
references
References 10 publications
1
61
0
Order By: Relevance
“…In this work, we enhance the learning capability of our prior work RR-DnCNN [20] by adopting the concept of skip connections [23]. Particularly, from the straightforward RR-DnCNN, we redesign the network architecture to have an ushaped form and utilize up-sampling skip connections to pass the useful features captured by restoration to reconstruction.…”
Section: E Skip Connectionsmentioning
confidence: 99%
See 4 more Smart Citations
“…In this work, we enhance the learning capability of our prior work RR-DnCNN [20] by adopting the concept of skip connections [23]. Particularly, from the straightforward RR-DnCNN, we redesign the network architecture to have an ushaped form and utilize up-sampling skip connections to pass the useful features captured by restoration to reconstruction.…”
Section: E Skip Connectionsmentioning
confidence: 99%
“…• We proposed a degradation-aware technique [20] treating the original LR as a transitional ground-truth to entirely solve the degradation from compression and up-sampling in down-sampling based video coding. • On which compression configuration for training, we proved that the RA provides various degradation enough to cover other types.…”
Section: F Contributionsmentioning
confidence: 99%
See 3 more Smart Citations