swMATH ID: 44025
Software Authors: Matias Tassano, Julie Delon, Thomas Veit
Description: DVDnet: A Fast Network for Deep Video Denoising. In this paper, we propose a state-of-the-art video denoising algorithm based on a convolutional neural network architecture. Previous neural network based approaches to video denoising have been unsuccessful as their performance cannot compete with the performance of patch-based methods. However, our approach outperforms other patch-based competitors with significantly lower computing times. In contrast to other existing neural network denoisers, our algorithm exhibits several desirable properties such as a small memory footprint, and the ability to handle a wide range of noise levels with a single network model. The combination between its denoising performance and lower computational load makes this algorithm attractive for practical denoising applications. We compare our method with different state-of-art algorithms, both visually and with respect to objective quality metrics. The experiments show that our algorithm compares favorably to other state-of-art methods. Video examples, code and models are publicly available at https://github.com/m-tassano/dvdnet
Homepage: https://arxiv.org/abs/1906.11890
Source Code:  https://github.com/m-tassano/dvdnet
Dependencies: Python
Keywords: Computer Vision; Pattern Recognition; arXiv_cs.CV; Image and Video Processing; arXiv_eess.IV
Related Software: DnCNN; FastDVDnet; ViDeNN; PatchMatch; FFDNet; MemNet; ImageNet; PyTorch; Caffe; U-Net; BSDS; darch; TensorFlow; VGGFace2; FOCNet; ISTA-Net; AlexNet; FSIM; cuDNN; MatConvNet
Cited in: 2 Documents

Citations by Year