Filters








8 Hits in 1.9 sec

ChromaGAN: Adversarial Picture Colorization with Semantic Class Distribution [article]

Patricia Vitoria, Lara Raad, Coloma Ballester
<span title="2020-01-20">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
This network is framed in an adversarial model that learns to colorize by incorporating perceptual and semantic understanding of color and class distributions.  ...  In this paper, we propose an adversarial learning colorization approach coupled with semantic information.  ...  We thank the support of NVIDIA Corporation for the donation of GPUs used in this work, Rafael Grompone von Gioi for valuable suggestions and José Lezama for his help with the user study.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1907.09837v2">arXiv:1907.09837v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/epflbppgivg25di2y5c7ikiwyi">fatcat:epflbppgivg25di2y5c7ikiwyi</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200902065632/https://arxiv.org/pdf/1907.09837v2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/14/48/1448f2d44dc9dbcb7475ca8f83a473b26ebb6aba.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1907.09837v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

ChromaGAN: Adversarial Picture Colorization with Semantic Class Distribution

Patricia Vitoria, Lara Raad, Coloma Ballester
<span title="">2020</span> <i title="IEEE"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/wsjivbkuezdvxdnrhihbwjrxlu" style="color: black;">2020 IEEE Winter Conference on Applications of Computer Vision (WACV)</a> </i> &nbsp;
This network is framed in an adversarial model that learns to colorize by incorporating perceptual and semantic understanding of color and class distributions.  ...  In this paper, we propose an adversarial learning colorization approach coupled with semantic information.  ...  We thank the support of NVIDIA Corporation for the donation of GPUs used in this work, Rafael Grompone von Gioi for valuable suggestions and José Lezama for his help with the user study.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/wacv45572.2020.9093389">doi:10.1109/wacv45572.2020.9093389</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/wacv/VitoriaRB20.html">dblp:conf/wacv/VitoriaRB20</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ceqjuln3tvgrrinteqomsledi4">fatcat:ceqjuln3tvgrrinteqomsledi4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200710063751/https://openaccess.thecvf.com/content_WACV_2020/papers/Vitoria_ChromaGAN_Adversarial_Picture_Colorization_with_Semantic_Class_Distribution_WACV_2020_paper.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/46/62/4662eb7e7611d5304fea9f5d533328a98cf1732f.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/wacv45572.2020.9093389"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

Adversarial Edge-aware Image Colorization with Semantic Segmentation

Guangqian Kong, Huan Tian, Xun Duan, Huiyun Long
<span title="">2021</span> <i title="Institute of Electrical and Electronics Engineers (IEEE)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/q7qi7j4ckfac7ehf3mjbso4hne" style="color: black;">IEEE Access</a> </i> &nbsp;
To solve these problems, we propose a new adversarial edgeaware image colorization method with multitask output combined with semantic segmentation.  ...  In addition, we also use a specific color difference loss with characteristics of human visual observation that is combined with semantic segmentation loss and adversarial loss for training.  ...  [17] proposed an automatic end-to-end adversarial method combining GANs and semantic class distribution learning.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/access.2021.3056144">doi:10.1109/access.2021.3056144</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/23kwdkfmovfzrm6mjocvb32tke">fatcat:23kwdkfmovfzrm6mjocvb32tke</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210717201613/https://ieeexplore.ieee.org/ielx7/6287639/9312710/09345804.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/08/61/0861de467589439fb6ca4135434dd860cbc4832c.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/access.2021.3056144"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> ieee.com </button> </a>

Image Colorization Progress: A Review of Deep Learning Techniques for Automation of Colorization

<span title="2021-08-25">2021</span> <i title="The World Academy of Research in Science and Engineering"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/naqzxq5hurh2bp2pnvwitnnx44" style="color: black;">International Journal of Advanced Trends in Computer Science and Engineering</a> </i> &nbsp;
Image colorization is the process of taking an input gray- scale (black and white) image and then producing an output colorized image that represents the semantic color tones of the input.  ...  There have been different approaches to solve this problem using Convolutional Neural Networks as well as Generative Adversarial Networks.  ...  Patricia Vitoria et. al. [38] This paper [38] proposes an end-to-end adversarial learning approach with semantic class distribution learning called ChromaGAN to colorize a grayscale image.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.30534/ijatcse/2021/401042021">doi:10.30534/ijatcse/2021/401042021</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/auv2aew6fzbhdcnsvpk2duouna">fatcat:auv2aew6fzbhdcnsvpk2duouna</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210830093544/http://www.warse.org/IJATCSE/static/pdf/file/ijatcse401042021.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/37/64/37640df6ce2d2bfe09b16db3466573a1ccf12415.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.30534/ijatcse/2021/401042021"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

Wavelet Transform-assisted Adaptive Generative Modeling for Colorization [article]

Jin Li, Wanyun Li, Zichen Xu, Yuhao Wang, Qiegen Liu
<span title="2021-07-09">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Moreover, such a highly flexible generative model without adversarial optimization can execute colorization tasks better under dual consistency terms in wavelet domain, namely data-consistency and structure-consistency  ...  In the test phase, samples are iteratively generated via annealed Langevin dynamics with data and structure consistencies.  ...  [15] exploited features via an end-to-end self-supervised generative adversarial network that learns to colorize by incorporating perceptual and semantic understanding.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2107.04261v1">arXiv:2107.04261v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/f2vwnyxyrvcoxaax6mcxhxhkoy">fatcat:f2vwnyxyrvcoxaax6mcxhxhkoy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210714030042/https://arxiv.org/ftp/arxiv/papers/2107/2107.04261.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/c9/85/c9857fddee6817c06e6cbd41f2213be3925742ac.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2107.04261v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

A Review and Analysis of The Existing Literature on Monochromatic Photography Colorization Using Deep Learning

A.M. Adăscăliței
<span title="2021-12-15">2021</span> <i title="Babes-Bolyai University"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/6ives635drbhbgeaommsxl7f3q" style="color: black;">Studia Universitatis Babes-Bolyai: Series Informatica</a> </i> &nbsp;
It is universally known that, through the process of colorization, one aims at converting a monochrome image into one of color, usually because it was taken by the limited technology of previous decades  ...  We curated some of the most promising papers, published between 2016 and 2021, and centered our observations around software reliability, and key advancements in solutions employing Generative Adversarial  ...  Chromagan: Adversarial picture coloriza- tion with semantic class distribution, 2020. [46] Wang, L., Guo, S., Huang, W., Xiong, Y., and Qiao, Y.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.24193/subbi.2021.2.03">doi:10.24193/subbi.2021.2.03</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/7lwyk4erfnaahnb3fmjlqh2zgq">fatcat:7lwyk4erfnaahnb3fmjlqh2zgq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220102225145/http://www.cs.ubbcluj.ro/~studia-i/journal/journal/article/download/71/71" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/dc/6e/dc6ed0f7d56068c861d47cbb1c85af91ec6525b6.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.24193/subbi.2021.2.03"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> Publisher / doi.org </button> </a>

Analysis of Different Losses for Deep Learning Image Colorization [article]

Coloma Ballester, Aurélie Bugeau, Hernan Carrillo, Michaël Clément, Rémi Giraud, Lara Raad, Patricia Vitoria
<span title="2022-05-09">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Qualitative results exhibit more vivid colors when with Wasserstein GAN plus the L2 loss or again with the VGG-based LPIPS.  ...  Image colorization aims to add color information to a grayscale image in a realistic way. Recent methods mostly rely on deep learning strategies.  ...  This chapter was written together with another chapter called Analysis of Different Losses for Deep Learning Image Colorization [Ballester et al., 2022] .  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2204.02980v2">arXiv:2204.02980v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/i32u3zmpbrdmdox3rvmekecwma">fatcat:i32u3zmpbrdmdox3rvmekecwma</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220512235413/https://arxiv.org/pdf/2204.02980v2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/cc/e9/cce95c03a26e58868eeaadace68ed99a449b8509.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2204.02980v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Influence of Color Spaces for Deep Learning Image Colorization [article]

Coloma Ballester, Aurélie Bugeau, Hernan Carrillo, Michaël Clément, Rémi Giraud, Lara Raad, Patricia Vitoria
<span title="2022-04-06">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We then compare the results obtained with the same deep neural network architecture with RGB, YUV and Lab color spaces.  ...  based colorization?".  ...  This chapter was written together with another chapter of the current handbook, called Analysis of Different Losses for Deep Learning Image Colorization.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2204.02850v1">arXiv:2204.02850v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/kza24bcplrccfeczj5254nmttq">fatcat:kza24bcplrccfeczj5254nmttq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220511094800/https://arxiv.org/pdf/2204.02850v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/8b/4c/8b4c8ef6d7995af8b19d98450cd061bb13819b17.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2204.02850v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>