TY - GEN
T1 - ViDeNN
T2 - CVPR workshop on NTIRE: New Trends in Image Restoration and Enhancement
AU - Claus, Michele
AU - van Gemert, Jan
PY - 2019
Y1 - 2019
N2 - We propose ViDeNN: a CNN for Video Denoising without prior knowledge on the noise distribution (blind denoising). The CNN architecture uses a combination of spatial and temporal filtering, learning to spatially denoise the frames first and at the same time how to combine their temporal information, handling objects motion, brightness changes, low-light conditions and temporal inconsistencies. We demonstrate the importance of the data used for CNNs training, creating for this purpose a specific dataset for lowlight conditions. We test ViDeNN on common benchmarks and on self-collected data, achieving good results comparable with the state-of-the-art.
AB - We propose ViDeNN: a CNN for Video Denoising without prior knowledge on the noise distribution (blind denoising). The CNN architecture uses a combination of spatial and temporal filtering, learning to spatially denoise the frames first and at the same time how to combine their temporal information, handling objects motion, brightness changes, low-light conditions and temporal inconsistencies. We demonstrate the importance of the data used for CNNs training, creating for this purpose a specific dataset for lowlight conditions. We test ViDeNN on common benchmarks and on self-collected data, achieving good results comparable with the state-of-the-art.
UR - http://www.scopus.com/inward/record.url?scp=85083316103&partnerID=8YFLogxK
U2 - 10.1109/CVPRW.2019.00235
DO - 10.1109/CVPRW.2019.00235
M3 - Conference contribution
SN - 978-1-7281-2507-7
T3 - IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
SP - 1843
EP - 1852
BT - Proceedings - 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2019
Y2 - 17 June 2019 through 17 June 2019
ER -