Deep Joint Image Filtering

By Yijun Li, Jia-Bin Huang, Narendra Ahuja, Ming-Hsuan Yang. European Conference on Computer Vision, 2016

297 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/9bc0d4609fadc139480096ca95772bd82303a985

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

Classification-Driven Dynamic Image Enhancement (2017, methodology): “Reversing the effect of these degradations in order to obtain sharp images is currently an active area of research [2, 22, 37].”
DRIT++: Diverse Image-to-Image Translation via Disentangled Representations (2019, background): “…problems, such as colorization (Larsson et al. 2016; Zhang et al. 2016) (grayscale→ color), super-resolution (Lai et al. 2017; Ledig et al. 2017; Li et al. 2016, 2019) (low-resolution → high-resolution), and photorealistic image synthesis (Chen and Koltun 2017; Park et al. 2019; Wang et al.…”
Learning Blind Video Temporal Consistency (2018, background): “Recent advances of deep convolutional neural networks (CNNs) have led to the development of many powerful image processing techniques including, image filtering [30,37], enhancement [10,24,38], style transfer [17,23,29], colorization [19,41], and general image-to-image translation tasks [21,27,43].”
Fast Image Processing with Fully-Convolutional Networks (2017, methodology): “Deep networks have been used for denoising [39, 11, 3], super-resolution [10, 19, 40, 42, 41, 48, 50], deblurring [74], restoration of images corrupted by dirt or rain [22], example-based non-photorealistic stylization [30, 70, 40], joint image filtering [49], dehazing [64], and demosaicking [31].”
FastFCN: Rethinking Dilated Convolution in the Backbone for Semantic Segmentation (2019, methodology): “However, the proposed JPU is designed for processing feature maps with a large number of channels while [17, 31] are specially designed for processing 3-channel images, which fail to capture the complex relations in high dimensional feature maps.”
Dynamic Scene Deblurring Using Spatially Variant Recurrent Neural Networks (2018, background): “Recently, deep learning has been widely used in many low-level vision problems, such as denoising [1, 20, 45], super-resolution[4, 35, 13, 14, 15, 43, 31], dehazing [27], derain/dedirt [6, 5], edge-preserving filtering [39, 18], and image deblurring (non-blind [28, 38, 44] and blind [29, 2, 42]).”
NAS-DIP: Learning Deep Image Prior with Neural Architecture Search (2020, background): “, single image super-resolution [44,45,46], image denoising [12,49,82], joint filtering [50]), and image synthesis (e.”
Fast End-to-End Trainable Guided Filter (2018, methodology): “The Role of Guided Filtering Layer To verify the effectiveness of the proposed guided ﬁltering layer, we replace it with DJF [31], which is a complex CNN designed for joint image upsampling and achieves the state-of-the-art performance among many ﬁlters.”
Pixel-Adaptive Convolutional Neural Networks (2019, methodology): “We found this training setup to be superior to the one recommended in DJF [26], and also compare with our own implementation of it under such a setting (“DJF (Our impl.)” in Tab.”
Diverse Image-to-Image Translation via Disentangled Representations (2018, background): “Many vision and graphics problems can be formulated as I2I translation problems, such as colorization [22,44] (grayscale → color), superresolution [24,21,25] (low-resolution→ high-resolution), and photorealistic image synthesis [6,40] (label→ image).”