# DN-ResNet: Efficient Deep Residual Network for Image Denoising

arXiv: https://arxiv.org/abs/1810.06766 · HTML: https://mlsanity.com/paper/1810.06766/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Oct 2018.

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

- [FastLLVE: Real-Time Low-Light Video Enhancement with Intensity-Aware Lookup Table](https://mlsanity.com/paper/2308.06749/) (2023)
- [Deep Joint Demosaicing and High Dynamic Range Imaging within a Single Shot](https://mlsanity.com/paper/2111.07281/) (2021)
- [Weighted Anisotropic-Isotropic Total Variation for Poisson Denoising](https://mlsanity.com/paper/2307.00439/) (2023)
- [A Multi-Head Convolutional Neural Network With Multi-path Attention improves Image Denoising](https://mlsanity.com/paper/2204.12736/) (2022)
- [Blind-Spot Guided Diffusion for Self-supervised Real-World Denoising](https://mlsanity.com/paper/2509.16091/) (2025)
- [Real Image Restoration via Structure-preserving Complementarity Attention](https://mlsanity.com/paper/2207.13879/) (2022)
- [Considering Image Information and Self-similarity: A Compositional Denoising Network](https://mlsanity.com/paper/2209.06417/) (2022)
- [A new transformation for embedded convolutional neural network approach toward real-time servo motor overload fault-detection](https://mlsanity.com/paper/2304.04005/) (2023)
- [Semantic Image Completion and Enhancement using GANs](https://mlsanity.com/paper/2307.14748/) (2023)

## Abstract (arXiv)

A deep learning approach to blind denoising of images without complete knowledge of the noise statistics is considered. We propose DN-ResNet, which is a deep convolutional neural network (CNN) consisting of several residual blocks (ResBlocks). With cascade training, DN-ResNet is more accurate and more computationally efficient than the state of art denoising networks. An edge-aware loss function is further utilized in training DN-ResNet, so that the denoising results have better perceptive quality compared to conventional loss function. Next, we introduce the depthwise separable DN-ResNet (DS-DN-ResNet) utilizing the proposed Depthwise Seperable ResBlock (DS-ResBlock) instead of standard ResBlock, which has much less computational cost. DS-DN-ResNet is incrementally evolved by replacing the ResBlocks in DN-ResNet by DS-ResBlocks stage by stage. As a result, high accuracy and good computational efficiency are achieved concurrently. Whereas previous state of art deep learning methods focused on denoising either Gaussian or Poisson corrupted images, we consider denoising images having the more practical Poisson with additive Gaussian noise as well. The results show that DN-ResNets are more efficient, robust, and perform better denoising than current state of art deep learning methods, as well as the popular variants of the BM3D algorithm, in cases of blind and non-blind denoising of images corrupted with Poisson, Gaussian or Poisson-Gaussian noise. Our network also works well for other image enhancement task such as compressed image restoration.