This paper addresses the challenge of keeping up with the ever-increasing graphical complexity of video games and introduces a deep-learning approach to mitigating it. As games get more and more demanding in terms of their graphics, it becomes increasingly difficult to maintain high-quality images while also ensuring good performance. This is where deep learning super sampling (DLSS) comes in. The paper explains how DLSS works, including the use of convolutional autoencoder neural networks and various other techniques and technologies. It also covers how the network is trained and optimized, as well as how it incorporates temporal antialiasing and frame generation techniques to enhance the final image quality. We will also discuss the effectiveness of these techniques as well as compare their performance to running at native resolutions.
{"title":"Deep-Learning Realtime Upsampling Techniques in Video Games","authors":"Biruk Mengistu","doi":"10.61366/2576-2176.1127","DOIUrl":"https://doi.org/10.61366/2576-2176.1127","url":null,"abstract":"This paper addresses the challenge of keeping up with the ever-increasing graphical complexity of video games and introduces a deep-learning approach to mitigating it. As games get more and more demanding in terms of their graphics, it becomes increasingly difficult to maintain high-quality images while also ensuring good performance. This is where deep learning super sampling (DLSS) comes in. The paper explains how DLSS works, including the use of convolutional autoencoder neural networks and various other techniques and technologies. It also covers how the network is trained and optimized, as well as how it incorporates temporal antialiasing and frame generation techniques to enhance the final image quality. We will also discuss the effectiveness of these techniques as well as compare their performance to running at native resolutions.","PeriodicalId":498881,"journal":{"name":"Scholarly Horizons University of Minnesota Morris Undergraduate Journal","volume":"194 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136084995","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}
Biometrics are used to help keep users’ data private. There are many different biometric systems, all dealing with a unique attribute of a user, such as fingerprint, face, retina, iris and voice recognition. Fingerprint biometric systems, specifically match-in-database, have universally become the most implemented biometric system. To make these systems more secure, threat models are used to identify potential attacks and ways to mitigate them. This paper introduces a threat model for match-in-database fingerprint authentication systems. It also describes some of the most frequent attacks these systems come across and some possible mitigation efforts that can be adapted to keep the systems more secure.
{"title":"Possible Attacks on Match-In-Database Fingerprint Authentication","authors":"Jadyn Sondrol","doi":"10.61366/2576-2176.1129","DOIUrl":"https://doi.org/10.61366/2576-2176.1129","url":null,"abstract":"Biometrics are used to help keep users’ data private. There are many different biometric systems, all dealing with a unique attribute of a user, such as fingerprint, face, retina, iris and voice recognition. Fingerprint biometric systems, specifically match-in-database, have universally become the most implemented biometric system. To make these systems more secure, threat models are used to identify potential attacks and ways to mitigate them. This paper introduces a threat model for match-in-database fingerprint authentication systems. It also describes some of the most frequent attacks these systems come across and some possible mitigation efforts that can be adapted to keep the systems more secure.","PeriodicalId":498881,"journal":{"name":"Scholarly Horizons University of Minnesota Morris Undergraduate Journal","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136084994","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}
Face swapping involves replacing the face in one image (the target) with a face in a different image (the source) while maintaining the pose and expression of the target face. Previous methods of face swapping required extensive computer power and man hours. As such, new methods are being developed that are quicker, less resource intensive, and more accessible to the non-expert. This paper provides background information on key methods used for face swapping and outlines three recently developed approaches: one based on generative adversarial networks, one based on linear 3D morphable models, and one based on encoder-decoders.
{"title":"Exploring Methods Used in Face Swapping","authors":"Joshua Eklund","doi":"10.61366/2576-2176.1120","DOIUrl":"https://doi.org/10.61366/2576-2176.1120","url":null,"abstract":"Face swapping involves replacing the face in one image (the target) with a face in a different image (the source) while maintaining the pose and expression of the target face. Previous methods of face swapping required extensive computer power and man hours. As such, new methods are being developed that are quicker, less resource intensive, and more accessible to the non-expert. This paper provides background information on key methods used for face swapping and outlines three recently developed approaches: one based on generative adversarial networks, one based on linear 3D morphable models, and one based on encoder-decoders.","PeriodicalId":498881,"journal":{"name":"Scholarly Horizons University of Minnesota Morris Undergraduate Journal","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136180043","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：