Restoring an Image Taken through a Window Covered with Dirt or Rain

By David Eigen, Dilip Krishnan, Rob Fergus. 2013

462 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

Instance-Sensitive Fully Convolutional Networks (2016, background): “These fully convolutional models are naturally applicable for image restoration problems, such as denoising [16], super-resolution [17], and others [18], where each output pixel is a real-number regressor of intensity values.”
RefineNet: Multi-path Refinement Networks for High-Resolution Semantic Segmentation (2016, background): “, depth estimation [15, 13, 33], image restoration [14], image super-resolution [12].”
Discovering Hidden Factors of Variation in Deep Networks (2014, background): “One of the goals of representation learning is to find an efficient representation of input data that simplifies tasks such as object classification [1] or image restoration [2].”
Joint Rain Detection and Removal from a Single Image with Contextualized Deep Networks (2020, methodology): “There are also some recent works on bad weather restoration or image enhancement, such as dehazing [36], [37], raindrop and dirt removal [38], [39], light enhancement [40], [41] and moderate rain removal [1], [22], [42], [43].”
Image De-Raining Transformer (2022, methodology): “For raindrop removal, we compare against Eigen’s model [104], Pix2Pix [105], AttentGAN [102] and Quan’s network[106].”
ALL Snow Removed: Single Image Desnowing Algorithm Using Hierarchical Dual-tree Complex Wavelet Representation and Contradict Channel Loss (2021, background): “[35], DesnowNet [1], and JSTASR [2] (GAN-based method).”
Removing Rain from Single Images via a Deep Detail Network (2017, methodology): “Figure 12: Comparison with deep learning method [9].”
Clearing the Skies: A Deep Network Architecture for Single-Image Rain Removal (2016, methodology): “As mentioned [6] proposed directly using a CNN to removing dirt and drops from a window [6].”
Learning a Deep Convolutional Network for Image Super-Resolution (2014, background): “More closely related to our work, the convolutional neural network is applied for natural image denoising [12] and removing noisy patterns (dirt/rain) [6].”
Fast End-to-End Trainable Guided Filter (2018, background): “rocessing tasks, which largely advanced the state-ofthe-art performance. Such tasks include image denoising [40], image demosaicking [41], image deblurring [42], image matting [43], rain drop removal [44], image dehazing [45], and image colorization [46]. The above methods mainly focus on solving on”
Lightweight Pyramid Networks for Image Deraining (2018, background): “In [29], a related work based on deep learning is introduced to remove static raindrops and dirt spots from pictures taken through windows.”
All in One Bad Weather Removal Using Architectural Search (2020, background): “’s [5] train a CNN with pairs of raindrop-degraded images and the corresponding raindrop-free images.”
Bidirectional Recurrent Convolutional Networks for Multi-Frame Super-Resolution (2015, background): “[12] demonstrate the effectiveness of CNN for image denoising with certain patterns.”
Deep Convolutional Neural Network for Image Deconvolution (2014, methodology): “Previous de-noise neural network [14, 15, 16] cannot be directly adopted since deconvolution may involve many neighboring pixels and result in a very complex energy function with nonlinear degradation.”
A Neural Approach to Blind Motion Deblurring (2016, methodology): “We begin by considering the differences between predicting deconvolution filter coefficients and regressing directly to pixel intensities xp[n], as was done in most prior neural restoration methods [10,11,12,13].”