Details
| Original language | English |
|---|---|
| Title of host publication | IEEE International Symposium on Circuits and Systems, ISCAS 2022 |
| Publisher | Institute of Electrical and Electronics Engineers Inc. |
| Pages | 511-515 |
| Number of pages | 5 |
| ISBN (electronic) | 9781665484855 |
| ISBN (print) | 978-1-6654-8486-2 |
| Publication status | Published - 2022 |
| Event | 2022 IEEE International Symposium on Circuits and Systems, ISCAS 2022 - Austin, United States Duration: 27 May 2022 → 1 Jun 2022 |
Publication series
| Name | Proceedings - IEEE International Symposium on Circuits and Systems |
|---|---|
| Volume | 2022-May |
| ISSN (Print) | 0271-4310 |
Abstract
In this paper we introduce an error concealment method for VVC that error-conceals B-frames based on the neural frame interpolation network RIFE. The network is trained using the BVI-DVC dataset to infer even full-HD frames. We integrate our proposed model in the VVC reference software VTM for its evaluation. The average error of a whole GOP with a single corrupted frame is decreased by 15% and 24% in terms of PSNR measurement compared to block matching and frame copy, respectively. To our knowledge, our approach is currently the best performing error concealment algorithm for single slice per B-frame settings.
Keywords
- error concealment, video coding, VVC
ASJC Scopus subject areas
- Engineering(all)
- Electrical and Electronic Engineering
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
IEEE International Symposium on Circuits and Systems, ISCAS 2022. Institute of Electrical and Electronics Engineers Inc., 2022. p. 511-515 (Proceedings - IEEE International Symposium on Circuits and Systems; Vol. 2022-May).
Research output: Chapter in book/report/conference proceeding › Conference contribution › Research › peer review
}
TY - GEN
T1 - Neural Network-based Error Concealment for B-Frames in VVC
AU - Benjak, Martin
AU - Aust, Niklas
AU - Samayoa, Yasser
AU - Ostermann, Jorn
PY - 2022
Y1 - 2022
N2 - In this paper we introduce an error concealment method for VVC that error-conceals B-frames based on the neural frame interpolation network RIFE. The network is trained using the BVI-DVC dataset to infer even full-HD frames. We integrate our proposed model in the VVC reference software VTM for its evaluation. The average error of a whole GOP with a single corrupted frame is decreased by 15% and 24% in terms of PSNR measurement compared to block matching and frame copy, respectively. To our knowledge, our approach is currently the best performing error concealment algorithm for single slice per B-frame settings.
AB - In this paper we introduce an error concealment method for VVC that error-conceals B-frames based on the neural frame interpolation network RIFE. The network is trained using the BVI-DVC dataset to infer even full-HD frames. We integrate our proposed model in the VVC reference software VTM for its evaluation. The average error of a whole GOP with a single corrupted frame is decreased by 15% and 24% in terms of PSNR measurement compared to block matching and frame copy, respectively. To our knowledge, our approach is currently the best performing error concealment algorithm for single slice per B-frame settings.
KW - error concealment
KW - video coding
KW - VVC
UR - http://www.scopus.com/inward/record.url?scp=85142529092&partnerID=8YFLogxK
U2 - 10.1109/ISCAS48785.2022.9937956
DO - 10.1109/ISCAS48785.2022.9937956
M3 - Conference contribution
AN - SCOPUS:85142529092
SN - 978-1-6654-8486-2
T3 - Proceedings - IEEE International Symposium on Circuits and Systems
SP - 511
EP - 515
BT - IEEE International Symposium on Circuits and Systems, ISCAS 2022
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2022 IEEE International Symposium on Circuits and Systems, ISCAS 2022
Y2 - 27 May 2022 through 1 June 2022
ER -