A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Filters
Unpaired Image Enhancement Featuring Reinforcement-Learning-Controlled Image Editing Software
[article]
2019
arXiv
pre-print
Preserved Fulltext
To incorporate image editing software into a GAN, we propose a reinforcement learning framework where the generator works as the agent that selects the software's parameters and is rewarded when it fools ...
This paper tackles unpaired image enhancement, a task of learning a mapping function which transforms input images into enhanced images in the absence of input-output image pairs. ...
To utilize image editing software in a GAN, we propose a reinforcement learning (RL) framework where the generator works as the agent controlling the software. ...
arXiv:1912.07833v1
fatcat:hrjmzvsshjaw3isf3qhg5sfbnq
Unpaired Image Enhancement Featuring Reinforcement-Learning-Controlled Image Editing Software
2020
PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
To incorporate image editing software into a GAN, we propose a reinforcement learning framework where the generator works as the agent that selects the software's parameters and is rewarded when it fools ...
This paper tackles unpaired image enhancement, a task of learning a mapping function which transforms input images into enhanced images in the absence of input-output image pairs. ...
To utilize image editing software in a GAN, we propose a reinforcement learning (RL) framework where the generator works as the agent controlling the software. ...
doi:10.1609/aaai.v34i07.6790
fatcat:5rnmzd6ruveyhnvm4vqpjglo7e
Exposure: A White-Box Photo Post-Processing Framework
[article]
2018
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
As it is difficult for users to acquire paired images that reflect their retouching preferences, we present in this paper a deep learning approach that is instead trained on unpaired data, namely a set ...
To address this problem, previous works have proposed automatic retouching systems based on supervised learning from paired training images acquired before and after manual editing. ...
In contrast to the low-level image properties represented by handcrafted features, the features from deep learning encode high-level semantic information, from which contextdependent edits can be learned ...
arXiv:1709.09602v2
fatcat:2kx5a34cz5ahbdfbcqdb2o4lwy
Learning Image-adaptive 3D Lookup Tables for High Performance Photo Enhancement in Real-time
2020
IEEE Transactions on Pattern Analysis and Machine Intelligence
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2020 pre-print arXiv:2009.14468v1 fatcat:vxnvvtmytvhuzi62w7slm554vq
usually manually tuned and fixed in camera imaging pipeline or photo editing tools. ...
Recent years have witnessed the increasing popularity of learning-based photo enhancement methods. ...
Satoshi and Toshihiko [11] employed a similar reinforcement learning strategy to learn an unpaired photo enhancement model. In addition to employing predefined operators, Hu et al. ...
doi:10.1109/tpami.2020.3026740
pmid:32976094
fatcat:3eohl4sq5zhrlebvw2s5xe7ciq
Exposure
2018
ACM Transactions on Graphics
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
In contrast to the low-level image properties represented by handcrafted features, the features from deep learning encode high-level semantic information, from which contextdependent edits can be learned ...
Most of these methods extract handcrafted features, such as intensity distributions and scene brightness, from an input image and learn to determine editing parameters with respect to them. ...
doi:10.1145/3181974
fatcat:s3pf7fdi25hqncvga2gjbfjdzu
Very Lightweight Photo Retouching Network with Conditional Sequential Modulation
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2022 accepted arXiv:2104.06279v2 fatcat:sy73pwlgyzad3lfvvbu2i7kz4y
In addition to achieve global photo retouching, the proposed framework can be easily extended to learn local enhancement effects. ...
In practice, photo retouching can be accomplished by a series of image processing operations. ...
In [47] , Satoshi and Toshihiko incorporated image editing software (such as Adobe Photoshop) into a GANbased reinforcement learning framework, where the generator worked as the agent to select the software's ...
arXiv:2104.06279v1
fatcat:u355vv2gufhm5jhcprusyiepmi
Conditional Sequential Modulation for Efficient Global Image Retouching
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Photo retouching aims at enhancing the aesthetic visual quality of images that suffer from photographic defects such as over/under exposure, poor contrast, inharmonious saturation. ...
The base network acts like an MLP that processes each pixel independently and the condition network extracts the global features of the input image to generate a condition vector. ...
., style transfer, image enhancement, unpaired learning) as the above mentioned methods.
Multiple Styles and Strength Control Photo retouching is a highly ill-posed problem. ...
arXiv:2009.10390v1
fatcat:zfkqhq6iufdhtdgq5fgee3bt3m
Flexible Piecewise Curves Estimation for Photo Enhancement
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
The method is also appealing as it is not limited to paired training data, thus it can flexibly learn rich enhancement styles from unpaired data. ...
The proposed method improves efficiency without compromising the enhancement quality and losing details in the original image. ...
Learning-based methods are popular for photo enhancement. Earlier work such as Yan et al. [10] learn specific enhancement styles given the features of color and semantic context. ...
arXiv:2010.13412v1
fatcat:x4tzuscaubfghbcvw5g4r72evi
Better Understanding: Stylized Image Captioning with Style Attention and Adversarial Training
2020
Symmetry
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
These two parts further enhance the learning ability of the model through adversarial learning. Our experiment has achieved effective performance on the benchmark dataset. ...
At the same time, we use back-reinforcement to evaluate the degree of consistency between the generated stylized captions with the image knowledge and specified style, respectively. ...
It can improve the model's ability that controls the style of generated captions. Although STrans already can generate style captions, its capabilities still need to be further enhanced. ...
doi:10.3390/sym12121978
fatcat:ck64mqm2wbblhndc2opshudjgi
Learning Tone Curves for Local Image Enhancement
2022
IEEE Access
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Tone curves are commonly used by photo-editing software and offer an intuitive representation to photographers, facilitating subsequent customization of the image. ...
Bridging the gap between global and local methods, we propose a local tone mapping network (LTMNet) that learns a grid of tone curves to locally enhance an image. ...
Similarly, [15] uses RL and unpaired images. ...
doi:10.1109/access.2022.3178745
fatcat:sbiemj4cfndcbbrk7mrkywkp74
ReLLIE: Deep Reinforcement Learning for Customized Low-Light Image Enhancement
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
To tackle these two challenges, this paper presents a novel deep reinforcement learning based method, dubbed ReLLIE, for customized low-light enhancement. ...
As ReLLIE learns a policy instead of one-one image translation, it can handle various low-light measurements and provide customized enhanced outputs by flexibly applying the policy different times. ...
the pixel coordinates. ( (x); A(x)) outputs the enhanced image at x, using the learned feature parameter A(x), which has the same size as the image. ...
arXiv:2107.05830v1
fatcat:irqt24s4ercdjoe3lvxkvztx2y
Diverse and Adjustable Versatile Image Enhancer
2021
IEEE Access
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
To establish better control in terms of enhancement level, we propose a more general form of adaptive instance normalization and loss functions, which can afford even extreme image editing. ...
To fill this void, we propose a novel framework, Diverse and adjustable Versatile Image Enhancer (DaVIE), that learns from multiple ER images simultaneously. ...
[29] presented unsupervised image enhancement method using GAN. By using a reinforcement learning, Park et al. [30] proposed a global image modification model. ...
doi:10.1109/access.2021.3084339
fatcat:sbu3unkryzgvdbycbrgahiazrm
Learning by Planning: Language-Guided Global Image Editing
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Recently, language-guided global image editing draws increasing attention with growing application potentials. ...
Hence, we propose a novel operation planning algorithm to generate possible editing sequences from the target image as pseudo ground truth. ...
To enable interpretable editing, [15] introduces a reinforcement learning (RL) framework with known editing operations for automatic image retouching trained from unpaired images. ...
arXiv:2106.13156v1
fatcat:m7xc5urrbreo7da4s2c7jnl364
Neural reactivity tracks fear generalization gradients
2013
Biological Psychology
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Insofar as the transfer of fear responses from threatrelated stimuli to potentially innocuous cues is a common feature in anxiety disorders (Lissek et al., 2008) , fear generalization may be a key learning ...
This direct comparison showed enhanced activation in the anterior insula, SMA, cingulate gyrus, caudate, thalamus and frontal areas. ...
doi:10.1016/j.biopsycho.2011.12.007
pmid:22200657
fatcat:qark7tykxvedljss5adcrbybr4
Machine Vision for Improved Human-Robot Cooperation in Adverse Underwater Conditions
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Other Versions
The difficulties are exacerbated by a host of non-linear image distortions caused by the vulnerabilities of underwater light propagation (e.g., wavelength-dependent attenuation, absorption, and scattering ...
The research outcomes entail novel design and efficient implementation of the underlying vision and learning-based algorithms with extensive field experimental validations and feasibility analyses for ...
Hence, the design of adaptable solutions to combat degraded vision (e.g., via online learning or reinforcement learning) has not been explored in the literature. ...
arXiv:1911.07623v2
fatcat:tb7voaqrlbgtfgzvdwvjfr64vu
« Previous
Showing results 1 — 15 out of 796 results