Automatic Photo Adjustment Using Deep Neural Networks

By Zhicheng Yan, H. Zhang, Baoyuan Wang, Sylvain Paris, Yizhou Yu. ACM Transactions on Graphics, 2014

298 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/47ae44f066a4e98a9f59c7e7eb94babb011bd5a8

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

Fast End-to-End Trainable Guided Filter (2018, background): “[42] use a fully-connected network that operates on each pixel separately with hand-crafted features as input.”
Deep Photo Enhancer: Unpaired Learning for Image Enhancement from Photographs with GANs (2018, background): “[23] proposed the first deep-learning-based method for photo adjustment.”
Deep Joint Rain Detection and Removal from a Single Image (2016, background): “These applications include denoising [35, 6, 7, 21, 1], completion [38], super-resolution [11, 12, 10, 31], deblurring [32], deconvolution [39] and style transfer [17, 40], etc.”
A Survey of Human-in-the-loop for Machine Learning (2021, background): “The research field of image enhancement has attracted ample attention from researchers in recent years, especially after the emergence of deep neural network algorithms [146, 147, 148].”
Manipulating Attributes of Natural Scenes via Hallucination (2018, background): “Yan et al. [2016] introduce the first automatic photo adjustment framework based on deep neural networks.”
Fast Image Processing with Fully-Convolutional Networks (2017, background): “[77] also applied deep networks to image adjustment.”
Real-time user-guided image colorization with learned deep priors (2017, background): “Recently, neural networks have shown impressive results for various image processing tasks, such as photo enhancement (Yan et al. 2016), sketch simplification (Simo-Serra et al. 2016), style transfer (Gatys et al. 2016; Selim et al. 2016), in-painting (Pathak et al. 2016), image blending (Zhu et…”
Underexposed Photo Enhancement Using Deep Illumination Estimation (2019, background): “[29] constructed the semantic map to achieve semantic-aware photo enhancement.”
Faceshop (2018, methodology): “Recently, numerous deep learning techniques have been proposed for global editing applications such as general image enhancing [Gharbi et al. 2017; Yan et al. 2016], grayscale to color transformation [Iizuka et al.”
Exposure (2017, methodology): “For photo retouching, CNNs have been utilized for spatially varying color mapping based on semantic information together with handcrafted global and local features (Yan et al. 2016), and for color constancy (Hu 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].”
Joint Rain Detection and Removal from a Single Image with Contextualized Deep Networks (2020, background): “These applications include denoising [32, 5, 6, 20, 1], completion [35], super-resolution [10, 11, 9, 29], deblurring [30], deconvolution [36] and style transfer [16, 37], etc.”
Deep Image Harmonization (2017, methodology): “Context information has been utilized in several image editing tasks, such as image enhancement [6, 29], image editing [27] and image inpainting [20].”
SNR-Aware Low-light Image Enhancement (2022, background): “Many learning-based low-light image enhancement approaches were proposed in recent years [2,14,20,22,29,31,42,48–50, 52, 53, 59, 60, 62, 63].”
Learned perceptual image enhancement (2017, background): “Image denoising [6], deblurring [34], super-resolution [7], and tonal adjustments [35] are examples of this generic paradigm.”
Deep bilateral learning for real-time image enhancement (2017, methodology): “We report mean L 2 error in L*a*b* space (lower is better) for retouches by the 5 photographers (A,B,C,D,E) in the MIT “FiveK” dataset, though previous work only presents results on photographer C [Hwang et al. 2012; Yan et al. 2016].”
An Experiment-Based Review of Low-Light Image Enhancement Methods (2020, methodology): “For example, Yan et al. proposed the ﬁrst deep-learning-based method for photo adjustment [253].”
Low-Light Image Enhancement via a Deep Hybrid Network (2019, background): “Recently, deep convolutional neural networks (CNNs) have been applied to image enhancement [3], [4], [16]–[24].”
Deep Colorization (2015, background): “It has recently been demonstrated that high-level understanding of an image is of great use for low-level vision problems ( e.g. image enhancement [18], edge detection [19]).”