Variational Denoising Network: Toward Blind Noise Modeling and Removal

By Zongsheng Yue, Hongwei Yong, Qian Zhao, Lei Zhang, Deyu Meng. Neural Information Processing Systems, 2019

374 citations recorded by the source corpus.

Blind image denoising is an important yet very challenging problem in computer vision due to the complicated acquisition process of real images. In this work we propose a new variational inference method, which integrates both noise estimation and image denoising into a unique Bayesian framework, for blind image denoising. Specifically, an approximate posterior, parameterized by deep neural networks, is presented by taking the intrinsic clean image and noise variances as latent variables conditioned on the input noisy image. This posterior provides explicit parametric forms for all its involved hyper-parameters, and thus can be easily implemented for blind image denoising with automatic noise estimation for the test noisy image. On one hand, as other data-driven deep learning methods, our method, namely variational denoising network (VDN), can perform denoising efficiently due to its explicit form of posterior expression. On the other hand, VDN inherits the advantages of traditional model-driven approaches, especially the good generalization capability of generative models. VDN has good interpretability and can be flexibly utilized to estimate and remove complicated non-i.i.d. noise collected in real scenarios. Comprehensive experiments are performed to substantiate the superiority of our method in blind image denoising.

Subfields: Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/696205a3c87bd0cb4bb8d8cacc437ebcfcdb07e3

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

In Media Technology

Citations in the corpus

Restormer: Efficient Transformer for High-Resolution Image Restoration (2021, neutral): “Method DnCNN BM3D CBDNet* RIDNet* AINDNet* VDN SADNet* DANet+* CycleISP* MIRNet DeamNet* MPRNet DAGL Uformer Restormer Dataset [101] [15] [25] [6] [35] [89] [12] [90] [91] [92] [63] [93] [55] [80] (Ours)”
Image De-Raining Transformer (2022, methodology): “On the other hand, our work primarily focuses on establishing a transformer-based method for single image de-TABLE [114] Model BM3D[115] DnCNN[38] VDN[116] DANet[117] CycleISP[118] MIRNet[119] DeamNet[120] MPRNet[79] DAGL[121] Uformer-S raining.”
Deep Generalized Unfolding Networks for Image Restoration (2022, methodology): “Real image denoising performance (y-axis) of our DGUNet and some recent denoisers (VDNet [75], GDANet [76], AINDNet [33], MIRNet [78], DeamNet [53], MPRNet [79]) under different parameter capacities (x-axis) on DND [52] dataset.”
Deep Learning on Image Denoising: An overview (2019, neutral): “One technique for resolving this 35.58 CIMM [12] 36.04 CBDNet [71] 37.72 VDN [251] 39.38 DRDN [192] 39.40 AGAN [131] 38.13 problem, is dilated convolution, which not only contributions to higher performance and efﬁciency, but is also very effective for mining more edge information.”
MAXIM: Multi-Axis MLP for Image Processing (2022, methodology): “Visual examples for image denoising on SIDD [2] among VDN [104], DANet [105], MIRNet [107], CycleISP [106], MPRNet [108], and the proposed MAXIM-3S.”
DiffBIR: Towards Blind Image Restoration with Generative Diffusion Prior (2023, methodology): “VDNet [68] proposes to implement noise estimation and denoising simultaneously based on the variational denoising network.”
Uformer: A General U-Shaped Transformer for Image Restoration (2021, methodology): “We compare Uformer with 8 state-of-the-art denoising methods, including the feature-based BM3D [12] and seven learning-based methods: RID-Net [4], VDN [70], CycleISP [72], NBNet [9], DANet [71], MIRNet [73], and MPRNet [74].”
Multi-Stage Progressive Image Restoration (2021, methodology): “Noisy BM3D [16] CBDNet [28] VDN [84] RIDNet [4]”
HiFaceGAN: Face Renovation via Collaborative Suppression and Replenishment (2020, background): “rsatility, robustness and generalization capability of our proposed HiFaceGAN. 2 RELATED WORKS 2.1 Non-Blind Face Restoration Image restoration consists of a variety of subtasks, such as denoising [1][60], deblurring [25][26] and compression artifact removal [7][39]. In particular, image super resol”
Learning Enriched Features for Real Image Restoration and Enhancement (2020, methodology): “Noisy CBDNet [39] RIDNet [5] VDN [118] MIRNet (Ours) Reference”