Pub Date : 2024-10-22DOI: 10.1007/s11263-024-02251-z
Edoardo Mello Rella, Ajad Chhatkuli, Ender Konukoglu, Luc Van Gool
Neural implicit fields have recently shown increasing success in representing, learning and analysis of 3D shapes. Signed distance fields and occupancy fields are still the preferred choice of implicit representations with well-studied properties, despite their restriction to closed surfaces. With neural networks, unsigned distance fields as well as several other variations and training principles have been proposed with the goal to represent all classes of shapes. In this paper, we develop a novel and yet a fundamental representation considering unit vectors in 3D space and call it Vector Field (VF). At each point in (mathbb {R}^3), VF is directed to the closest point on the surface. We theoretically demonstrate that VF can be easily transformed to surface density by computing the flux density. Unlike other standard representations, VF directly encodes an important physical property of the surface, its normal. We further show the advantages of VF representation, in learning open, closed, or multi-layered surfaces. We show that, thanks to the continuity property of the neural optimization with VF, a separate distance field becomes unnecessary for extracting surfaces from the implicit field via Marching Cubes. We compare our method on several datasets including ShapeNet where the proposed new neural implicit field shows superior accuracy in representing any type of shape, outperforming other standard methods. Codes are available at https://github.com/edomel/ImplicitVF.
{"title":"Neural Vector Fields for Implicit Surface Representation and Inference","authors":"Edoardo Mello Rella, Ajad Chhatkuli, Ender Konukoglu, Luc Van Gool","doi":"10.1007/s11263-024-02251-z","DOIUrl":"https://doi.org/10.1007/s11263-024-02251-z","url":null,"abstract":"<p>Neural implicit fields have recently shown increasing success in representing, learning and analysis of 3D shapes. Signed distance fields and occupancy fields are still the preferred choice of implicit representations with well-studied properties, despite their restriction to closed surfaces. With neural networks, unsigned distance fields as well as several other variations and training principles have been proposed with the goal to represent all classes of shapes. In this paper, we develop a novel and yet a fundamental representation considering unit vectors in 3D space and call it Vector Field (VF). At each point in <span>(mathbb {R}^3)</span>, VF is directed to the closest point on the surface. We theoretically demonstrate that VF can be easily transformed to surface density by computing the flux density. Unlike other standard representations, VF directly encodes an important physical property of the surface, its normal. We further show the advantages of VF representation, in learning open, closed, or multi-layered surfaces. We show that, thanks to the continuity property of the neural optimization with VF, a separate distance field becomes unnecessary for extracting surfaces from the implicit field via Marching Cubes. We compare our method on several datasets including ShapeNet where the proposed new neural implicit field shows superior accuracy in representing any type of shape, outperforming other standard methods. Codes are available at https://github.com/edomel/ImplicitVF.\u0000</p>","PeriodicalId":13752,"journal":{"name":"International Journal of Computer Vision","volume":null,"pages":null},"PeriodicalIF":19.5,"publicationDate":"2024-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142487455","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-22DOI: 10.1109/tip.2024.3482185
Kevin Zhang, Sakshum Kulshrestha, Christopher Metzler
{"title":"A Scalable Training Strategy for Blind Multi-Distribution Noise Removal","authors":"Kevin Zhang, Sakshum Kulshrestha, Christopher Metzler","doi":"10.1109/tip.2024.3482185","DOIUrl":"https://doi.org/10.1109/tip.2024.3482185","url":null,"abstract":"","PeriodicalId":13217,"journal":{"name":"IEEE Transactions on Image Processing","volume":null,"pages":null},"PeriodicalIF":10.6,"publicationDate":"2024-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142487456","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Integrated Communication, Navigation, and Remote Sensing in LEO Networks with Vehicular Applications","authors":"Min Sheng, Chongtao Guo, Lei Huang","doi":"10.1109/mwc.007.2400140","DOIUrl":"https://doi.org/10.1109/mwc.007.2400140","url":null,"abstract":"","PeriodicalId":13342,"journal":{"name":"IEEE Wireless Communications","volume":null,"pages":null},"PeriodicalIF":12.9,"publicationDate":"2024-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142487381","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-22DOI: 10.1109/mcom.001.2400185
Sujit Kumar Sahu, Molka Gharbaoui, Anna Lina Ruscelli, Gabriele Cecchetti, Andrea Sgambelluri, Piero Castoldi
{"title":"Remote Medical Support in Emergency Scenarios: A WebRTC-Based Solution","authors":"Sujit Kumar Sahu, Molka Gharbaoui, Anna Lina Ruscelli, Gabriele Cecchetti, Andrea Sgambelluri, Piero Castoldi","doi":"10.1109/mcom.001.2400185","DOIUrl":"https://doi.org/10.1109/mcom.001.2400185","url":null,"abstract":"","PeriodicalId":55030,"journal":{"name":"IEEE Communications Magazine","volume":null,"pages":null},"PeriodicalIF":11.2,"publicationDate":"2024-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142487384","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-22DOI: 10.1109/tii.2024.3477561
Jun Min, Zhiwei Gao, Lei Wang
{"title":"Application and Research of Music Generation System Based on CVAE and Transformer-XL in Video Background Music","authors":"Jun Min, Zhiwei Gao, Lei Wang","doi":"10.1109/tii.2024.3477561","DOIUrl":"https://doi.org/10.1109/tii.2024.3477561","url":null,"abstract":"","PeriodicalId":13301,"journal":{"name":"IEEE Transactions on Industrial Informatics","volume":null,"pages":null},"PeriodicalIF":12.3,"publicationDate":"2024-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142487406","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-10-22DOI: 10.1109/mcom.001.2400076
Li Dong, Feibo Jiang, Yubo Peng, Kezhi Wang, Kun Yang, Cunhua Pan, Robert Schober
{"title":"LAMBO: Large AI Model Empowered Edge Intelligence","authors":"Li Dong, Feibo Jiang, Yubo Peng, Kezhi Wang, Kun Yang, Cunhua Pan, Robert Schober","doi":"10.1109/mcom.001.2400076","DOIUrl":"https://doi.org/10.1109/mcom.001.2400076","url":null,"abstract":"","PeriodicalId":55030,"journal":{"name":"IEEE Communications Magazine","volume":null,"pages":null},"PeriodicalIF":11.2,"publicationDate":"2024-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142487473","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}