Filters








46 Hits in 2.1 sec

FeGAN

Rachid Guerraoui, Arsany Guirguis, Anne-Marie Kermarrec, Erwan Le Merrer
<span title="2020-12-07">2020</span> <i title="ACM"> Proceedings of the 21st International Middleware Conference </i> &nbsp;
In particular, FeGAN achieves up to 5× throughput gain with 1.5× less bandwidth compared to the state-of-the-art GAN distributed approach (named MD-GAN), while scaling to at least one order of magnitude  ...  Existing approaches to distribute Generative Adversarial Networks (GANs) either (i) fail to scale for they typically put the two components of a GAN (the generator and the discriminator) on different machines  ...  We propose FeGAN, a distributed middleware that enables GANs to scale and cope with GAN specific issues such as mode collapse and vanishing gradients.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/3423211.3425688">doi:10.1145/3423211.3425688</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/pmh6wk6wj5cvblypdjtzui6axy">fatcat:pmh6wk6wj5cvblypdjtzui6axy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210717032558/https://os.zhdk.cloud.switch.ch/tind-tmp-epfl/4a06e6e6-8d2b-4511-b327-e81b0bc3b4e2?response-content-disposition=attachment%3B%20filename%2A%3DUTF-8%27%27FeGAN.pdf&amp;response-content-type=application%2Fpdf&amp;AWSAccessKeyId=ded3589a13b4450889b2f728d54861a6&amp;Expires=1626519192&amp;Signature=yfqzqjEiQk9onebUNtCejF%2FwjXc%3D" 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/ba/e0/bae0f47944dc3f75a78d1d0b863ffefe12012231.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/3423211.3425688"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> acm.org </button> </a>

Technology Section of the White Paper on the Status and Future of Ground-based TeV Gamma-ray Astronomy [article]

K. Byrum, J. Buckley, S. Bugayov, B. Dingus, S. Fegan, S. Funk, E. Hays, J. Holder, D. Horan, A. Konopelko, H. Krawczynski, F. Krennrich (+5 others)
<span title="2008-10-24">2008</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
The R&D for IACT could be finalized on a time scale of between 3 (IACTs).  ...  high quantum efficiency, multi-anode photomultipliers, multi channel plates, Si photomultipliers, Geiger mode Si detectors, and hybrid photodetectors with semiconductor photocathodes such as GaAsP or In-GaN  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/0810.4367v1">arXiv:0810.4367v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/dhutyq7sifdghnup4qd4qtkocm">fatcat:dhutyq7sifdghnup4qd4qtkocm</a> </span>
<a target="_blank" rel="noopener" href="https://archive.org/download/arxiv-0810.4367/0810.4367.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> File Archive [PDF] </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/0810.4367v1" 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>

Extreme Face Inpainting with Sketch-Guided Conditional GAN [article]

Nilesh Pandey, Andreas Savakis
<span title="2021-05-13">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In our proposed conditional GAN, we pass the conditional input in every layer of the encoder while maintaining consistency in the distributions between the learned weights and the incoming conditional  ...  We propose to tackle this extreme inpainting task with a conditional Generative Adversarial Network (GAN) that utilizes structural information, such as edges, as a prior condition.  ...  ., N represent N input samples from different distributions p i (x i ), i = 1, ...N, t is the target, F are fake labels for generated images and R are real labels for ground truth images. min G L GAN =  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2105.06033v1">arXiv:2105.06033v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/hhpptki7pzdpdegvkbfcpnevdu">fatcat:hhpptki7pzdpdegvkbfcpnevdu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210516213200/https://arxiv.org/pdf/2105.06033v1.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/b8/f4/b8f46108160b98799f8ae85777999e5249be677f.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2105.06033v1" 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>

An Unsupervised Approach towards Varying Human Skin Tone Using Generative Adversarial Networks [article]

Debapriya Roy, Diganta Mukherjee, Bhabatosh Chanda
<span title="2020-10-30">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
SC-FEGAN [19] proposed a method that generates images as per user provided inputs e.g., in the form of free-form mask, sketch or color. This is also based on GAN.  ...  , to be coming from the data distribution rather than the generator distribution.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2010.16092v1">arXiv:2010.16092v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/6qtdu6zbgbebjkxubfmxkzzuu4">fatcat:6qtdu6zbgbebjkxubfmxkzzuu4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201103000945/https://arxiv.org/pdf/2010.16092v1.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/3d/c8/3dc8b2eac93d515d09ba0f3d19246d560b36d870.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2010.16092v1" 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>

Fashion Editing with Adversarial Parsing Learning [article]

Haoye Dong, Xiaodan Liang, Yixuan Zhang, Xujie Zhang, Zhenyu Xie, Bowen Wu, Ziqi Zhang, Xiaohui Shen, Jian Yin
<span title="2019-09-28">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
A new attention normalization layer is further applied at multiple scales in the decoder of the inpainting network to enhance the quality of the synthesized image.  ...  In this paper, we propose a novel Fashion Editing Generative Adversarial Network (FE-GAN), which is capable of manipulating fashion images by free-form sketches and sparse color strokes.  ...  Recently, another face editing system SC-FEGAN [32] is proposed, which generates high-quality images when users provide the free-form as input. However, SC-FEGAN is designed for face editing.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1906.00884v2">arXiv:1906.00884v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/3i2kxaal7rh65dh7kw6absgila">fatcat:3i2kxaal7rh65dh7kw6absgila</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200830035439/https://arxiv.org/pdf/1906.00884v2.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/1f/5b/1f5bef1be0653b7c5cb71f6f72bf527487ffd558.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1906.00884v2" 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>

Complement Face Forensic Detection and Localization with FacialLandmarks [article]

Kritaphat Songsri-in, Stefanos Zafeiriou
<span title="2019-10-12">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
The fake images are generated from various GANs methods, namely DCGANs, LSGANs, BEGANs, WGAN-GP, ProGANs, and StyleGANs.  ...  Recently, Generative Adversarial Networks (GANs) and image manipulating methods are becoming more powerful and can produce highly realistic face images beyond human recognition which have raised significant  ...  Generative Adversarial Networks (GANs) Generative Adversarial Networks (GANs) [11] are generative models that consist of two competing networks: a generator and a discriminator.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1910.05455v1">arXiv:1910.05455v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/27ydvc34wbdjldbpc5gieuazme">fatcat:27ydvc34wbdjldbpc5gieuazme</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200827030641/https://arxiv.org/pdf/1910.05455v1.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/98/cc/98ccd8f0f239f018893b9e1787846bf41f8563d9.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1910.05455v1" 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>

Diverse facial inpainting guided by exemplars [article]

Wanglong Lu, Hanli Zhao, Xianta Jiang, Xiaogang Jin, Min Wang, Jiankai Lyu, Kaijie Shi
<span title="2022-02-15">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
This paper introduces EXE-GAN, a novel diverse and interactive facial inpainting framework, which can not only preserve the high-quality visual effect of the whole image but also complete the face image  ...  comparison of our EXE-GAN with SC-FEGAN [11] and LaFIn [10] .  ...  We then randomly distribute one of these groups to a user.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2202.06358v2">arXiv:2202.06358v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/cxr7paxfhrbrhhsmtdn2uzr42a">fatcat:cxr7paxfhrbrhhsmtdn2uzr42a</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220216032041/https://arxiv.org/pdf/2202.06358v1.pdf" title="fulltext PDF download [not primary version]" 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] <span style="color: #f43e3e;">&#10033;</span> <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/91/f6/91f6ad36f6fb8fcb731a7645b087467ecfab37fd.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2202.06358v2" 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 State-of-the-Art Review on Image Synthesis with Generative Adversarial Networks

Lei Wang, Wei Chen, Wenjia Yang, Fangming Bi, Fei Richard Yu
<span title="">2020</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;
The purpose of this review is to provide insights into the research on GANs and to present the various applications based on GANs in different scenarios.  ...  Then, we discuss the challenges faced by GANs and introduce some methods to deal with these problems.  ...  Moreover, two domains that share the same content distribution with different style distributions.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/access.2020.2982224">doi:10.1109/access.2020.2982224</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/p5uxjh4cybfw5grp6ldhkpukrm">fatcat:p5uxjh4cybfw5grp6ldhkpukrm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201108115234/https://ieeexplore.ieee.org/ielx7/6287639/8948470/09043519.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/b0/70/b0703b8e0377beac2dbd04a2e3b2de7350b896b3.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/access.2020.2982224"> <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>

The Image Local Autoregressive Transformer [article]

Chenjie Cao, Yuxin Hong, Xiang Li, Chengrong Wang, Chengming Xu, XiangYang Xue, Yanwei Fu
<span title="2021-10-18">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Recently, AutoRegressive (AR) models for the whole image generation empowered by transformers have achieved comparable or even better performance to Generative Adversarial Networks (GANs).  ...  (a) Reference (b) Target (e) Posewarp (f) MR-Net (g) Taming (h) iLAT (c) PATN (d) PN-GAN (a) Reference (b) Target (c) Taming (d) Taming* (f) iLAT (e) SC-FEGAN Qualitative Results Non-Iconic Pose Guiding  ...  Besides, inpainting-based SC-FEGAN achieves unstable results in rows 3 and 4.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2106.02514v2">arXiv:2106.02514v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/tajzufodwzeujpytwfq7wropj4">fatcat:tajzufodwzeujpytwfq7wropj4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20211021075832/https://arxiv.org/pdf/2106.02514v2.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/ae/8d/ae8dceba0700cb85293666f712b5cdaf483d5053.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2106.02514v2" 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>

Generative Adversarial Network for Multi Facial Attributes Translation

Jun Liu, Xiaoyang Liu, Yanjun Feng
<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;
The smaller the value of FID, the closer the two Gaussian distributions are, and the better the performance of GAN.  ...  MMD can measure the distance between the training dataset distribution and the generated dataset and then use this distance as the evaluation index of GAN.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/access.2021.3112895">doi:10.1109/access.2021.3112895</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/twl5wk2lbbbs3agddazl5wpfhy">fatcat:twl5wk2lbbbs3agddazl5wpfhy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210917223211/https://ieeexplore.ieee.org/ielx7/6287639/6514899/09537764.pdf?tp=&amp;arnumber=9537764&amp;isnumber=6514899&amp;ref=" 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/b1/5b/b15b65ff992ec6fc7f98e02532a461ac0275765a.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/access.2021.3112895"> <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>

MichiGAN: Multi-Input-Conditioned Hair Image Generation for Portrait Editing [article]

Zhentao Tan and Menglei Chai and Dongdong Chen and Jing Liao and Qi Chu and Lu Yuan and Sergey Tulyakov and Nenghai Yu
<span title="2020-10-30">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this paper, we present MichiGAN (Multi-Input-Conditioned Hair Image GAN), a novel conditional image generation method for interactive portrait hair manipulation.  ...  Despite the recent success of face image generation with GANs, conditional hair editing remains challenging due to the under-explored complexity of its geometry and appearance.  ...  Starting from a random latent code, GANs can generate fake images with the same distribution as natural images in a target domain.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2010.16417v1">arXiv:2010.16417v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/kwpceg2hfbfavbfydwsi6locwq">fatcat:kwpceg2hfbfavbfydwsi6locwq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201103002124/https://arxiv.org/pdf/2010.16417v1.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/3d/df/3ddfa545f8a31be9a863b56a48bf971c653bf782.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2010.16417v1" 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>

Deep Plastic Surgery: Robust and Controllable Image Editing with Human-Drawn Sketches [article]

Shuai Yang, Zhangyang Wang, Jiaying Liu, Zongming Guo
<span title="2020-01-09">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In AdaIN [9] , styles are modelled as the mean and variance of the features and are transferred via distribution scaling and shifting (i.e., normalization+denormalization).  ...  of SC-FEGAN.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2001.02890v1">arXiv:2001.02890v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/emmztmf5zjfmvb6vb6ija5cvs4">fatcat:emmztmf5zjfmvb6vb6ija5cvs4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200321093906/https://arxiv.org/pdf/2001.02890v1.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] </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2001.02890v1" 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>

Studying Short-Range Correlations with Real Photon Beams at GlueX [article]

O. Hen, M. Patsyuk, E. Piasetzky, A. Schmidt, A. Somov, H. Szumila-Vance, L. B. Weinstein, D. Dutta, H. Gao, M. Amaryan, A. Ashkenazi, A. Beck (+50 others)
<span title="2020-10-03">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We have chosen to distribute the beam time between the different targets so as to obtain comparable discriminating power for transparency studies and scaling of SRC pairs; the larger nuclei have larger  ...  We refer to these as the 'SRC scaling coefficients'.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2009.09617v3">arXiv:2009.09617v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/awvbvvu2vbdvnpxtyngc6hbncu">fatcat:awvbvvu2vbdvnpxtyngc6hbncu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201008154313/https://arxiv.org/pdf/2009.09617v3.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] </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2009.09617v3" 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>

ForgeryNet: A Versatile Benchmark for Comprehensive Forgery Analysis [article]

Yinan He, Bei Gan, Siyu Chen, Yichun Zhou, Guojun Yin, Luchuan Song, Lu Sheng, Jing Shao, Ziwei Liu
<span title="2021-07-14">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
ForgeryNet is by far the largest publicly available deep face forgery dataset in terms of data-scale (2.9 million images, 221,247 videos), manipulations (7 image-level approaches, 8 video-level approaches  ...  MaskGAN [37] m,i/i GAN M/M editing record 512*512 portraits,mask SC-FEGAN [34] s,i/i GAN M/M sketch record 512*512 portraits,sketch DiscoFaceGAN [17] i/i CG+GAN M/M 3dmm attributes 1024  ...  ID-replaced DeepFakes FSGAN BlendFace FaceShifter ID-remained Target (a) (b) StarGAN2 MaskGAN StyleGAN2 SC-FEGAN DiscoFace GAN 2) ATVG-Net FirstOrder Motion Talking-headVideo 1) 2) 1) 3) SBS DSS !  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2103.05630v2">arXiv:2103.05630v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/b6gz6ugdmjhfnfawno2d6ummxa">fatcat:b6gz6ugdmjhfnfawno2d6ummxa</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210718054151/https://arxiv.org/pdf/2103.05630v2.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/1b/20/1b20d22cebe2d591530abd297b7d519176ebdfe5.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2103.05630v2" 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>

DeFLOCNet: Deep Image Editing via Flexible Low-level Controls [article]

Hongyu Liu, Ziyu Wan, Wei Huang, Yibing Song, Xintong Han, Jing Liao, Bing Jiang, Wei Liu
<span title="2021-03-23">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
GANs have a lasting influence on image editing development. In [22] , Invertible Conditional GANs are proposed to control high-level attributes of generated faces.  ...  We set different numbers of injection operations in the fusion branch for each scale, respectively.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2103.12723v1">arXiv:2103.12723v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/fg53ochbj5ab5dvv2yluvaredm">fatcat:fg53ochbj5ab5dvv2yluvaredm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210328002255/https://arxiv.org/pdf/2103.12723v1.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/18/69/18690ff821f98d2e5890544adbb91d32683054ba.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2103.12723v1" 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>
&laquo; Previous Showing results 1 &mdash; 15 out of 46 results