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.
|Title of host publication||CVPR workshop on NTIRE: New Trends in Image Restoration and Enhancement|
|Number of pages||10|
|Publication status||Published - 2019|
|Event||CVPR workshop on NTIRE: New Trends in Image Restoration and Enhancement: NTIRE 2019 - Long Beach, United States|
Duration: 17 Jun 2019 → 17 Jun 2019
|Workshop||CVPR workshop on NTIRE: New Trends in Image Restoration and Enhancement|
|Period||17/06/19 → 17/06/19|