ViDeNN: Deep Blind Video Denoising

24 Apr 2019  ·  Michele Claus, Jan van Gemert ·

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 low-light conditions. We test ViDeNN on common benchmarks and on self-collected data, achieving good results comparable with the state-of-the-art.

PDF Abstract

Datasets

CBSD68 RENOIR
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Color Image Denoising CBSD68 sigma10 Spatial-CNN PSNR 35.92 # 2
Compare
Color Image Denoising CBSD68 sigma15 Spatial-CNN PSNR 33.66 # 7
Compare
Color Image Denoising CBSD68 sigma25 Spatial-CNN PSNR 30.99 # 6
Compare
Color Image Denoising CBSD68 sigma35 Spatial-CNN PSNR 29.34 # 4
Compare
Color Image Denoising CBSD68 sigma5 Spatial-CNN PSNR 39.73 # 3
Compare
Color Image Denoising CBSD68 sigma50 Spatial-CNN PSNR 27.63 # 10
Compare

Methods
Add Remove

No methods listed for this paper. Add relevant methods here
Contact us on: hello@paperswithcode.com . Papers With Code is a free resource with all data licensed under CC-BY-SA.
Terms Data policy Cookies policy