TY - GEN
T1 - Kalman filtering of patches for frame-recursive video denoising
AU - Arias, Pablo
AU - Morel, Jean-Michel
N1 - Publication details (e.g. title, author(s), publication statuses and dates) are captured on an “AS IS” and “AS AVAILABLE” basis at the time of record harvesting from the data source. Suggestions for further amendments or supplementary information can be sent to [email protected].
PY - 2019/6/1
Y1 - 2019/6/1
N2 - A frame recursive video denoising method computes each output frame as a function of only the current noisy frame and the previous denoised output. Frame recursive methods were among the earliest approaches for video denoising. However in the last fifteen years they have been used almost exclusively for real-time applications with denoising performance far from being state-of-the-art. In this work we propose a simple frame recursive method which is fast, has a low memory complexity and achieves results competitive with more complex state-of-the-art methods that require processing several input frames for producing each output frame. Furthermore, in terms of visual quality, the proposed approach is able to recover many details that are missed by most non-recursive methods. As an additional contribution we also propose an off-line post-processing of the denoised video that boosts denoising quality and temporal consistency. © 2019 IEEE.
AB - A frame recursive video denoising method computes each output frame as a function of only the current noisy frame and the previous denoised output. Frame recursive methods were among the earliest approaches for video denoising. However in the last fifteen years they have been used almost exclusively for real-time applications with denoising performance far from being state-of-the-art. In this work we propose a simple frame recursive method which is fast, has a low memory complexity and achieves results competitive with more complex state-of-the-art methods that require processing several input frames for producing each output frame. Furthermore, in terms of visual quality, the proposed approach is able to recover many details that are missed by most non-recursive methods. As an additional contribution we also propose an off-line post-processing of the denoised video that boosts denoising quality and temporal consistency. © 2019 IEEE.
UR - http://www.scopus.com/inward/record.url?scp=85083306441&partnerID=8YFLogxK
UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-85083306441&origin=recordpage
U2 - 10.1109/CVPRW.2019.00243
DO - 10.1109/CVPRW.2019.00243
M3 - RGC 32 - Refereed conference paper (with host publication)
SN - 9781728125060
VL - 2019-June
T3 - IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
SP - 1917
EP - 1926
BT - Proceedings - 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2019
PB - IEEE Computer Society
T2 - 32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2019
Y2 - 16 June 2019 through 20 June 2019
ER -