FastDVDnet: Towards Real-Time Deep Video Denoising Without Flow Estimation

By Matias Tassano, Julie Delon, Thomas Veit. Computer Vision and Pattern Recognition, 2019

302 citations recorded by the source corpus.

In this paper, we propose a state-of-the-art video denoising algorithm based on a convolutional neural network architecture. Until recently, video denoising with neural networks had been a largely under explored domain, and existing methods could not compete with the performance of the best patch-based methods. The approach we introduce in this paper, called FastDVDnet, shows similar or better performance than other state-of-the-art competitors with significantly lower computing times. In contrast to other existing neural network denoisers, our algorithm exhibits several desirable properties such as fast runtimes, and the ability to handle a wide range of noise levels with a single network model. The characteristics of its architecture make it possible to avoid using a costly motion compensation stage while achieving excellent performance. 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.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/bece8923d7cdf3fb345ed551450bdaf470baadba

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

VRT: A Video Restoration Transformer (2022, methodology): “Third, for video denoising, we follow [28], [29] and train a non-blind denoising model using varying noise levels ( σ ∼ U ( 0 , 50 ) ) by concatenating the noise level map with the noisy video along the channel dimension.”