Pub Date : 2022-08-24DOI: 10.48550/arXiv.2208.11546
Shima Shahfar, Charalambos (Charis) Poullis
The Swapping Autoencoder achieved state-of-the-art performance in deep image manipulation and image-to-image translation. We improve this work by introducing a simple yet effective auxiliary module based on gradient reversal layers. The auxiliary module's loss forces the generator to learn to reconstruct an image with an all-zero texture code, encouraging better disentanglement between the structure and texture information. The proposed attribute-based transfer method enables refined control in style transfer while preserving structural information without using a semantic mask. To manipulate an image, we encode both the geometry of the objects and the general style of the input images into two latent codes with an additional constraint that enforces structure consistency. Moreover, due to the auxiliary loss, training time is significantly reduced. The superiority of the proposed model is demonstrated in complex domains such as satellite images where state-of-the-art are known to fail. Lastly, we show that our model improves the quality metrics for a wide range of datasets while achieving comparable results with multi-modal image generation techniques.
{"title":"Unsupervised Structure-Consistent Image-to-Image Translation","authors":"Shima Shahfar, Charalambos (Charis) Poullis","doi":"10.48550/arXiv.2208.11546","DOIUrl":"https://doi.org/10.48550/arXiv.2208.11546","url":null,"abstract":"The Swapping Autoencoder achieved state-of-the-art performance in deep image manipulation and image-to-image translation. We improve this work by introducing a simple yet effective auxiliary module based on gradient reversal layers. The auxiliary module's loss forces the generator to learn to reconstruct an image with an all-zero texture code, encouraging better disentanglement between the structure and texture information. The proposed attribute-based transfer method enables refined control in style transfer while preserving structural information without using a semantic mask. To manipulate an image, we encode both the geometry of the objects and the general style of the input images into two latent codes with an additional constraint that enforces structure consistency. Moreover, due to the auxiliary loss, training time is significantly reduced. The superiority of the proposed model is demonstrated in complex domains such as satellite images where state-of-the-art are known to fail. Lastly, we show that our model improves the quality metrics for a wide range of datasets while achieving comparable results with multi-modal image generation techniques.","PeriodicalId":91444,"journal":{"name":"Advances in visual computing : ... international symposium, ISVC ... : proceedings. International Symposium on Visual Computing","volume":"77 1","pages":"3-21"},"PeriodicalIF":0.0,"publicationDate":"2022-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89680267","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 : 2022-01-01DOI: 10.1007/978-3-031-20713-6_27
Konstantinos Bacharidis, Antonis A. Argyros
{"title":"Cross-Domain Learning in Deep HAR Models via Natural Language Processing on Action Labels","authors":"Konstantinos Bacharidis, Antonis A. Argyros","doi":"10.1007/978-3-031-20713-6_27","DOIUrl":"https://doi.org/10.1007/978-3-031-20713-6_27","url":null,"abstract":"","PeriodicalId":91444,"journal":{"name":"Advances in visual computing : ... international symposium, ISVC ... : proceedings. International Symposium on Visual Computing","volume":"45 1","pages":"347-361"},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78804763","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 : 2022-01-01DOI: 10.1007/978-3-031-20716-7_9
Kianoush Falahkheirkhah, Kevin Yeh, M. Confer, R. Bhargava
{"title":"DRB-Net: Dilated Residual Block Network for Infrared Image Restoration","authors":"Kianoush Falahkheirkhah, Kevin Yeh, M. Confer, R. Bhargava","doi":"10.1007/978-3-031-20716-7_9","DOIUrl":"https://doi.org/10.1007/978-3-031-20716-7_9","url":null,"abstract":"","PeriodicalId":91444,"journal":{"name":"Advances in visual computing : ... international symposium, ISVC ... : proceedings. International Symposium on Visual Computing","volume":"508 ","pages":"104-115"},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91459604","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 : 2022-01-01DOI: 10.1007/978-3-031-20713-6_3
Patricia L. Suárez, A. Sappa, Dario Carpio, Henry O. Velesaca, Francisca Burgos, Patricia Urdiales
{"title":"Deep Learning Based Shrimp Classification","authors":"Patricia L. Suárez, A. Sappa, Dario Carpio, Henry O. Velesaca, Francisca Burgos, Patricia Urdiales","doi":"10.1007/978-3-031-20713-6_3","DOIUrl":"https://doi.org/10.1007/978-3-031-20713-6_3","url":null,"abstract":"","PeriodicalId":91444,"journal":{"name":"Advances in visual computing : ... international symposium, ISVC ... : proceedings. International Symposium on Visual Computing","volume":"1 1","pages":"36-45"},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88933940","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 : 2022-01-01DOI: 10.1007/978-3-031-20716-7_27
A. Smith, Shengzhi Du, A. Kurien
{"title":"Overview on Machine Vision Based Surface Defect Detection and Quality Classification in the Leather Manufacturing Process","authors":"A. Smith, Shengzhi Du, A. Kurien","doi":"10.1007/978-3-031-20716-7_27","DOIUrl":"https://doi.org/10.1007/978-3-031-20716-7_27","url":null,"abstract":"","PeriodicalId":91444,"journal":{"name":"Advances in visual computing : ... international symposium, ISVC ... : proceedings. International Symposium on Visual Computing","volume":"49 1","pages":"344-356"},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83660254","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 : 2022-01-01DOI: 10.1007/978-3-031-20716-7_30
Farnaz Farahanipad, M. Nasr, Mohammad Rezaei, F. Kamangar, V. Athitsos, Manfred Huber
{"title":"2D Fingertip Localization on Depth Videos Using Paired Video-to-Video Translation","authors":"Farnaz Farahanipad, M. Nasr, Mohammad Rezaei, F. Kamangar, V. Athitsos, Manfred Huber","doi":"10.1007/978-3-031-20716-7_30","DOIUrl":"https://doi.org/10.1007/978-3-031-20716-7_30","url":null,"abstract":"","PeriodicalId":91444,"journal":{"name":"Advances in visual computing : ... international symposium, ISVC ... : proceedings. International Symposium on Visual Computing","volume":"56 1","pages":"381-392"},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81995464","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 : 2022-01-01DOI: 10.1007/978-3-031-20713-6_30
Jingtao Huang, T. Komuro
{"title":"End-to-End Deep Neural Network for Illumination Consistency and Global Illumination","authors":"Jingtao Huang, T. Komuro","doi":"10.1007/978-3-031-20713-6_30","DOIUrl":"https://doi.org/10.1007/978-3-031-20713-6_30","url":null,"abstract":"","PeriodicalId":91444,"journal":{"name":"Advances in visual computing : ... international symposium, ISVC ... : proceedings. International Symposium on Visual Computing","volume":"34 1","pages":"392-403"},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88492115","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 : 2022-01-01DOI: 10.1007/978-3-031-20713-6_28
Ying Zhu
{"title":"Visualizing Data Flows in Computer Graphics Programs for Code Comprehension and Debugging","authors":"Ying Zhu","doi":"10.1007/978-3-031-20713-6_28","DOIUrl":"https://doi.org/10.1007/978-3-031-20713-6_28","url":null,"abstract":"","PeriodicalId":91444,"journal":{"name":"Advances in visual computing : ... international symposium, ISVC ... : proceedings. International Symposium on Visual Computing","volume":"4 1","pages":"365-376"},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91247224","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 : 2022-01-01DOI: 10.1007/978-3-031-20713-6_34
Anwesh Kabiraj, Tanushree Meena, Pailla Balakrishna Reddy, S. Roy
{"title":"Detection and Classification of Lung Disease Using Deep Learning Architecture from X-ray Images","authors":"Anwesh Kabiraj, Tanushree Meena, Pailla Balakrishna Reddy, S. Roy","doi":"10.1007/978-3-031-20713-6_34","DOIUrl":"https://doi.org/10.1007/978-3-031-20713-6_34","url":null,"abstract":"","PeriodicalId":91444,"journal":{"name":"Advances in visual computing : ... international symposium, ISVC ... : proceedings. International Symposium on Visual Computing","volume":"28 1","pages":"444-455"},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77959419","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 : 2022-01-01DOI: 10.1007/978-3-031-20716-7_31
Yusuke Nonaka, Hideaki Uchiyama, H. Saito, S. Yachida, K. Iwamoto
{"title":"Difference-in-level Detection from RGB-D Images","authors":"Yusuke Nonaka, Hideaki Uchiyama, H. Saito, S. Yachida, K. Iwamoto","doi":"10.1007/978-3-031-20716-7_31","DOIUrl":"https://doi.org/10.1007/978-3-031-20716-7_31","url":null,"abstract":"","PeriodicalId":91444,"journal":{"name":"Advances in visual computing : ... international symposium, ISVC ... : proceedings. International Symposium on Visual Computing","volume":"33 1","pages":"393-406"},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74062250","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：