# Non-Local Video Denoising by CNN

arXiv: https://arxiv.org/abs/1811.12758 · HTML: https://mlsanity.com/paper/1811.12758/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Nov 2018.

## Built on by (most cited first, 9 of 9)

- [Neural Compression-Based Feature Learning for Video Restoration](https://mlsanity.com/paper/2203.09208/) (2022)
- [On the Generalization of BasicVSR++ to Video Deblurring and Denoising](https://mlsanity.com/paper/2204.05308/) (2022)
- [Real-time Streaming Video Denoising with Bidirectional Buffers](https://mlsanity.com/paper/2207.06937/) (2022)
- [Learning Task-Oriented Flows to Mutually Guide Feature Alignment in Synthesized and Real Video Denoising](https://mlsanity.com/paper/2208.11803/) (2022)
- [Coarse-to-Fine Video Denoising with Dual-Stage Spatial-Channel Transformer](https://mlsanity.com/paper/2205.00214/) (2022)
- [A Lightweight Structure Aimed to Utilize Spatial Correlation for Sparse-View CT Reconstruction](https://mlsanity.com/paper/2101.07613/) (2021)
- [DCS-RISR: Dynamic Channel Splitting for Efficient Real-world Image Super-Resolution](https://mlsanity.com/paper/2212.07613/) (2022)
- [Joint Flow And Feature Refinement Using Attention For Video Restoration](https://mlsanity.com/paper/2505.16434/) (2025)
- [Video Denoising in Fluorescence Guided Surgery](https://mlsanity.com/paper/2411.09798/) (2024)

## Abstract (arXiv)

Non-local patch based methods were until recently state-of-the-art for image denoising but are now outperformed by CNNs. Yet they are still the state-of-the-art for video denoising, as video redundancy is a key factor to attain high denoising performance. The problem is that CNN architectures are hardly compatible with the search for self-similarities. In this work we propose a new and efficient way to feed video self-similarities to a CNN. The non-locality is incorporated into the network via a first non-trainable layer which finds for each patch in the input image its most similar patches in a search region. The central values of these patches are then gathered in a feature vector which is assigned to each image pixel. This information is presented to a CNN which is trained to predict the clean image. We apply the proposed architecture to image and video denoising. For the latter patches are searched for in a 3D spatio-temporal volume. The proposed architecture achieves state-of-the-art results. To the best of our knowledge, this is the first successful application of a CNN to video denoising.