Pub Date : 2024-04-15DOI: 10.24425/bpasts.2024.150331
{"title":"150331","authors":"","doi":"10.24425/bpasts.2024.150331","DOIUrl":"https://doi.org/10.24425/bpasts.2024.150331","url":null,"abstract":"","PeriodicalId":503897,"journal":{"name":"Bulletin of the Polish Academy of Sciences Technical Sciences","volume":"59 18","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140700885","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-04-15DOI: 10.24425/bpasts.2024.150327
{"title":"150327","authors":"","doi":"10.24425/bpasts.2024.150327","DOIUrl":"https://doi.org/10.24425/bpasts.2024.150327","url":null,"abstract":"","PeriodicalId":503897,"journal":{"name":"Bulletin of the Polish Academy of Sciences Technical Sciences","volume":"4 4","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140699812","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-04-15DOI: 10.24425/bpasts.2024.150329
{"title":"150329","authors":"","doi":"10.24425/bpasts.2024.150329","DOIUrl":"https://doi.org/10.24425/bpasts.2024.150329","url":null,"abstract":"","PeriodicalId":503897,"journal":{"name":"Bulletin of the Polish Academy of Sciences Technical Sciences","volume":"6 3","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140699353","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-04-15DOI: 10.24425/bpasts.2024.150335
{"title":"150335","authors":"","doi":"10.24425/bpasts.2024.150335","DOIUrl":"https://doi.org/10.24425/bpasts.2024.150335","url":null,"abstract":"","PeriodicalId":503897,"journal":{"name":"Bulletin of the Polish Academy of Sciences Technical Sciences","volume":"22 10","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140699765","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-04-04DOI: 10.24425/bpasts.2024.150200
{"title":"150200","authors":"","doi":"10.24425/bpasts.2024.150200","DOIUrl":"https://doi.org/10.24425/bpasts.2024.150200","url":null,"abstract":"","PeriodicalId":503897,"journal":{"name":"Bulletin of the Polish Academy of Sciences Technical Sciences","volume":"5 5","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140741866","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-04-04DOI: 10.24425/bpasts.2024.150202
{"title":"150202","authors":"","doi":"10.24425/bpasts.2024.150202","DOIUrl":"https://doi.org/10.24425/bpasts.2024.150202","url":null,"abstract":"","PeriodicalId":503897,"journal":{"name":"Bulletin of the Polish Academy of Sciences Technical Sciences","volume":"16 5","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140744706","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-04-04DOI: 10.24425/bpasts.2024.150203
{"title":"150203","authors":"","doi":"10.24425/bpasts.2024.150203","DOIUrl":"https://doi.org/10.24425/bpasts.2024.150203","url":null,"abstract":"","PeriodicalId":503897,"journal":{"name":"Bulletin of the Polish Academy of Sciences Technical Sciences","volume":"23 7","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140741434","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-04-04DOI: 10.24425/bpasts.2024.150199
{"title":"150199","authors":"","doi":"10.24425/bpasts.2024.150199","DOIUrl":"https://doi.org/10.24425/bpasts.2024.150199","url":null,"abstract":"","PeriodicalId":503897,"journal":{"name":"Bulletin of the Polish Academy of Sciences Technical Sciences","volume":"13 17","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140745766","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-04-04DOI: 10.24425/bpasts.2024.150201
{"title":"150201","authors":"","doi":"10.24425/bpasts.2024.150201","DOIUrl":"https://doi.org/10.24425/bpasts.2024.150201","url":null,"abstract":"","PeriodicalId":503897,"journal":{"name":"Bulletin of the Polish Academy of Sciences Technical Sciences","volume":"8 4","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140743906","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-03-28DOI: 10.24425/bpasts.2024.150109
Sami Mahfoud, Messaoud Bengherabi, A. Daamouche, Elhocine Boutellaa, Abdenour Hadid
Face sketch synthesis (FSS) is considered as an image-to-image translation problem, where a face sketch is generated from an input face photo. FSS plays a vital role in video/image surveillance-based law enforcement. In this paper, motivated by the recent success of generative adversarial networks (GAN), we consider conditional GAN (cGAN) to approach the problem of face sketch synthesis. However, despite the powerful cGAN model’s ability to generate fine textures, low-quality inputs characterized by the facial sketches drawn by artists cannot offer realistic and faithful details and have unknown degradation due to the drawing process, while high-quality references are inaccessible or even unexistent. In this context, we propose an approach based on Generative Reference Prior (GRP) to improve the synthesized face sketch perception. Our proposed model, that we call cGAN-GRP, leverages diverse and rich priors encapsulated in a pre-trained face GAN for generating high-quality facial sketch synthesis. Extensive experiments on publicly available face databases using facial sketch recognition rate and image quality assessment metrics as criteria demonstrate the effectiveness of our proposed model compared to several state-of-the-art methods.
人脸素描合成（FSS）被认为是一个图像到图像的转换问题，即从输入的人脸照片生成人脸素描。FSS 在基于视频/图像监控的执法中发挥着重要作用。在本文中，受生成式对抗网络（GAN）最近取得成功的启发，我们考虑用条件 GAN（cGAN）来解决人脸草图合成问题。然而，尽管强大的 cGAN 模型具有生成精细纹理的能力，但以艺术家绘制的面部草图为特征的低质量输入无法提供逼真和忠实的细节，并且由于绘制过程而存在未知的退化，而高质量的参考则无法获取甚至根本不存在。在这种情况下，我们提出了一种基于生成参考先验（GRP）的方法来改善合成面部草图的感知。我们提出的模型被称为 cGAN-GRP，它利用预先训练好的人脸 GAN 中封装的多样而丰富的先验来生成高质量的人脸草图合成。以人脸草图识别率和图像质量评估指标为标准，在公开的人脸数据库上进行了广泛的实验，证明了我们提出的模型与几种最先进的方法相比非常有效。
{"title":"High-Quality Synthesized Face Sketch Using Generative Reference Prior","authors":"Sami Mahfoud, Messaoud Bengherabi, A. Daamouche, Elhocine Boutellaa, Abdenour Hadid","doi":"10.24425/bpasts.2024.150109","DOIUrl":"https://doi.org/10.24425/bpasts.2024.150109","url":null,"abstract":"Face sketch synthesis (FSS) is considered as an image-to-image translation problem, where a face sketch is generated from an input face photo. FSS plays a vital role in video/image surveillance-based law enforcement. In this paper, motivated by the recent success of generative adversarial networks (GAN), we consider conditional GAN (cGAN) to approach the problem of face sketch synthesis. However, despite the powerful cGAN model’s ability to generate fine textures, low-quality inputs characterized by the facial sketches drawn by artists cannot offer realistic and faithful details and have unknown degradation due to the drawing process, while high-quality references are inaccessible or even unexistent. In this context, we propose an approach based on Generative Reference Prior (GRP) to improve the synthesized face sketch perception. Our proposed model, that we call cGAN-GRP, leverages diverse and rich priors encapsulated in a pre-trained face GAN for generating high-quality facial sketch synthesis. Extensive experiments on publicly available face databases using facial sketch recognition rate and image quality assessment metrics as criteria demonstrate the effectiveness of our proposed model compared to several state-of-the-art methods.","PeriodicalId":503897,"journal":{"name":"Bulletin of the Polish Academy of Sciences Technical Sciences","volume":"7 2","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140372547","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：