File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1007/978-3-030-01264-9_35
- Scopus: eid_2-s2.0-85055703534
- WOS: WOS:000604454400035
- Find via
Supplementary
- Citations:
- Appears in Collections:
Conference Paper: Deep kalman filtering network for video compression artifact reduction
Title | Deep kalman filtering network for video compression artifact reduction |
---|---|
Authors | |
Keywords | Compression artifact reduction Deep neural network Kalman model Recursive filtering Video restoration |
Issue Date | 2018 |
Publisher | Springer |
Citation | 15th European Conference on Computer Vision (ECCV 2018), Munich, Germany, 8-14 September 2018. In Ferrari, V, Hebert, M, Sminchisescu, C, et al. (Eds.), Computer Vision - ECCV 2018: 15th European Conference, Munich, Germany, September 8-14, 2018, Proceedings, Part XIV, p. 591-608. Cham, Switzerland: Springer, 2018 How to Cite? |
Abstract | When lossy video compression algorithms are applied, compression artifacts often appear in videos, making decoded videos unpleasant for human visual systems. In this paper, we model the video artifact reduction task as a Kalman filtering procedure and restore decoded frames through a deep Kalman filtering network. Different from the existing works using the noisy previous decoded frames as temporal information in the restoration problem, we utilize the less noisy previous restored frame and build a recursive filtering scheme based on the Kalman model. This strategy can provide more accurate and consistent temporal information, which produces higher quality restoration results. In addition, the strong prior information of prediction residual is also exploited for restoration through a well designed neural network. These two components are combined under the Kalman framework and optimized through the deep Kalman filtering network. Our approach can well bridge the gap between the model-based methods and learning-based methods by integrating the recursive nature of the Kalman model and highly non-linear transformation ability of deep neural network. Experimental results on the benchmark dataset demonstrate the effectiveness of our proposed method. |
Persistent Identifier | http://hdl.handle.net/10722/321816 |
ISBN | |
ISSN | 2023 SCImago Journal Rankings: 0.606 |
ISI Accession Number ID | |
Series/Report no. | Lecture Notes in Computer Science ; 11218 LNCS Sublibrary. SL 6, Image Processing, Computer Vision, Pattern Recognition, and Graphics |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Lu, Guo | - |
dc.contributor.author | Ouyang, Wanli | - |
dc.contributor.author | Xu, Dong | - |
dc.contributor.author | Zhang, Xiaoyun | - |
dc.contributor.author | Gao, Zhiyong | - |
dc.contributor.author | Sun, Ming Ting | - |
dc.date.accessioned | 2022-11-03T02:21:38Z | - |
dc.date.available | 2022-11-03T02:21:38Z | - |
dc.date.issued | 2018 | - |
dc.identifier.citation | 15th European Conference on Computer Vision (ECCV 2018), Munich, Germany, 8-14 September 2018. In Ferrari, V, Hebert, M, Sminchisescu, C, et al. (Eds.), Computer Vision - ECCV 2018: 15th European Conference, Munich, Germany, September 8-14, 2018, Proceedings, Part XIV, p. 591-608. Cham, Switzerland: Springer, 2018 | - |
dc.identifier.isbn | 9783030012632 | - |
dc.identifier.issn | 0302-9743 | - |
dc.identifier.uri | http://hdl.handle.net/10722/321816 | - |
dc.description.abstract | When lossy video compression algorithms are applied, compression artifacts often appear in videos, making decoded videos unpleasant for human visual systems. In this paper, we model the video artifact reduction task as a Kalman filtering procedure and restore decoded frames through a deep Kalman filtering network. Different from the existing works using the noisy previous decoded frames as temporal information in the restoration problem, we utilize the less noisy previous restored frame and build a recursive filtering scheme based on the Kalman model. This strategy can provide more accurate and consistent temporal information, which produces higher quality restoration results. In addition, the strong prior information of prediction residual is also exploited for restoration through a well designed neural network. These two components are combined under the Kalman framework and optimized through the deep Kalman filtering network. Our approach can well bridge the gap between the model-based methods and learning-based methods by integrating the recursive nature of the Kalman model and highly non-linear transformation ability of deep neural network. Experimental results on the benchmark dataset demonstrate the effectiveness of our proposed method. | - |
dc.language | eng | - |
dc.publisher | Springer | - |
dc.relation.ispartof | Computer Vision - ECCV 2018: 15th European Conference, Munich, Germany, September 8-14, 2018, Proceedings, Part XIV | - |
dc.relation.ispartofseries | Lecture Notes in Computer Science ; 11218 | - |
dc.relation.ispartofseries | LNCS Sublibrary. SL 6, Image Processing, Computer Vision, Pattern Recognition, and Graphics | - |
dc.subject | Compression artifact reduction | - |
dc.subject | Deep neural network | - |
dc.subject | Kalman model | - |
dc.subject | Recursive filtering | - |
dc.subject | Video restoration | - |
dc.title | Deep kalman filtering network for video compression artifact reduction | - |
dc.type | Conference_Paper | - |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.doi | 10.1007/978-3-030-01264-9_35 | - |
dc.identifier.scopus | eid_2-s2.0-85055703534 | - |
dc.identifier.spage | 591 | - |
dc.identifier.epage | 608 | - |
dc.identifier.eissn | 1611-3349 | - |
dc.identifier.isi | WOS:000604454400035 | - |
dc.publisher.place | Cham, Switzerland | - |