Image Denoising and Inpainting with Deep Neural Networks

By Junyuan Xie, Linli Xu, Enhong Chen. 2012

1,465 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

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

Fixing the train-test resolution discrepancy (2019, background): “Convolutional Neural Networks [21] (CNNs) are used extensively in computer vision tasks such as image classification [20], object detection [30], inpainting [41], style transfer [11] and even image compression [31].”
Large Scale Image Completion via Co-Modulated Generative Adversarial Networks (2021, background): “Then, (Köhler et al., 2014; Ren et al., 2015; Xie et al., 2012) adopt deep neural networks for image completion; (Pathak et al., 2016) first exploits conditional GANs.”
Semantic Image Inpainting with Deep Generative Models (2016, neutral): “Unlike previous hand-crafted matching and editing, learning based methods have shown promising results [27, 38, 33, 22].”
Variational Approaches for Auto-Encoding Generative Adversarial Networks (2017, positive): “The prospect of marrying the two approaches (VAEs and GANs) comes with multiple benefits: auto-encoder based methods can be used to reconstruct data and thus can be used for inpainting [28] [43]; having an inference network allows our model to be used for representation learning [2], where we can le”
Deep Stereo: Learning to Predict New Views from the World's Imagery (2015, background): “One possible reason is the perceived inability of deep networks to generate pixels directly, but recent work on denoising [40], super-resolution [6], and rendering [23] suggests that this is a misconception.”
Video Frame Interpolation via Adaptive Separable Convolution (2017, methodology): “Our research is inspired by the success of applying deep learning to optical ﬂow estimation [2, 12, 16, 19, 50, 51, 52], artistic style transfer [17, 22, 28], and image enhancement [6, 9, 10, 46, 47, 55, 57, 62, 65].”
Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising (2016, neutral): “In [25], stacked sparse denoising auto-encoders method was adopted to handle Gaussian noise removal and achieved comparable results to K-SVD [5].”
Removing Rain from Single Images via a Deep Detail Network (2017, background): “The deep CNN has not only achieved success on high-level vision tasks [12, 13] but has also been extended to problems such as image denoising [34, 36], super-resolution [7, 19], reducing artifacts of compression [8], image inpainting [26] and image dehazing [27].”
Second-Order Adversarial Attack and Certifiable Robustness (2018, methodology): “However, we note that there have been notable efforts at developing robust DNNs to natural perturbations Xie et al. (2012); Zhang et al. (2017); yet, these methods failed to defend models from adversarial attacks, as they are not particularly designed for that task. Our framework allows us to adapt ”
Brief review of image denoising techniques (2019, methodology): “MLP-based image denoising models include auto-encoders proposed by Vincent et al. [104] and Xie et al. [105].”
AOD-Net: All-in-One Dehazing Network (2017, background): “Examples include image denoising [29], deblurring [20], and super resolution [28].”
Image inpainting through neural networks hallucinations (2016, methodology): “We note that specialized deep neural networks have previously been trained to solve inverse problems, such as denoising and blind inpainting [12].”
Deep Convolutional Framelets: A General Deep Learning Framework for Inverse Problems (2017, background): “While most of the existing inpainting networks are based on feed-forward network [70, 57, 73], our theory of the deep convolutional framelets leads to a recursive neural network (RNN) that gradually improved the image with CNN-based image restoration, making the algorithm more accurate for various m”
Deep Convolutional Neural Network for Image Deconvolution (2014, methodology): “2(b) and (c) show the results of SSDAE and CNN.”
Quantitative susceptibility mapping using deep neural network: QSMnet (2018, methodology): “Recently, deep learning using a neural network has been widely applied across multiple ﬁ elds including computer vision, computer assisted diagnosis, pattern recognition (Noh et al., 2015; Sermanet et al., 2013; Xie et al., 2012).”
Dirty Pixels: Optimizing Image Classification Architectures for Raw Sensor Data (2017, methodology): “We then applied the Inception-v4 classification network, one of the state-of-the-art models, to each noised and blurred validation set [Szegedy et al. 2016].”
Medical Image Denoising Using Convolutional Denoising Autoencoders (2016, methodology): “Xie et al. [28] used stacked sparse autoencoders for image denoising and inpainting, it performed at par with KSVD. Agostenelli et al. [1] experimented with adaptive multi column deep neural networks for image denoising, built using combination of stacked sparse autoencoders.”