发布求助
文献互助 智能选刊 最新文献

Colloques sur le traitement du signal et des images最新文献

筛选
英文 中文
Defining an action of SO(d)-rotations on images generated by projections of d-dimensional objects: Applications to pose inference with Geometric VAEs. 定义由d维物体投影生成的图像上的SO(d)-旋转动作:用几何VAEs进行姿态推理的应用。
Colloques sur le traitement du signal et des images Pub Date : 2022-09-01
Nicolas Legendre, Khanh Dao Duc, Nina Miolane
{"title":"Defining an action of <i>SO</i>(<i>d</i>)-rotations on images generated by projections of <i>d</i>-dimensional objects: Applications to pose inference with Geometric VAEs.","authors":"Nicolas Legendre,&nbsp;Khanh Dao Duc,&nbsp;Nina Miolane","doi":"","DOIUrl":"","url":null,"abstract":"<p><p>Recent advances in variational autoencoders (VAEs) have enabled learning latent manifolds as compact Lie groups, such as <i>SO</i>(<i>d</i>). Since this approach assumes that data lies on a subspace that is homeomorphic to the Lie group itself, we here investigate how this assumption holds in the context of images that are generated by projecting a <i>d</i>-dimensional volume with unknown pose in <i>SO</i>(<i>d</i>). Upon examining different theoretical candidates for the group and image space, we show that the attempt to define a group action on the data space generally fails, as it requires more specific geometric constraints on the volume. Using geometric VAEs, our experiments confirm that this constraint is key to proper pose inference, and we discuss the potential of these results for applications and future work.</p>","PeriodicalId":72637,"journal":{"name":"Colloques sur le traitement du signal et des images","volume":"28 ","pages":"329-332"},"PeriodicalIF":0.0,"publicationDate":"2022-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10354539/pdf/nihms-1823247.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"10226480","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Defining an action of SO(d)-rotations on images generated by projections of d-dimensional objects: Applications to pose inference with Geometric VAEs 定义由d维物体投影生成的图像上的SO(d)-旋转动作:用几何VAEs进行姿态推理的应用
Colloques sur le traitement du signal et des images Pub Date : 2022-07-23 DOI: 10.48550/arXiv.2207.11582
Nicolas Legendre, K. D. Duc, Nina Miolane
{"title":"Defining an action of SO(d)-rotations on images generated by projections of d-dimensional objects: Applications to pose inference with Geometric VAEs","authors":"Nicolas Legendre, K. D. Duc, Nina Miolane","doi":"10.48550/arXiv.2207.11582","DOIUrl":"https://doi.org/10.48550/arXiv.2207.11582","url":null,"abstract":"Recent advances in variational autoencoders (VAEs) have enabled learning latent manifolds as compact Lie groups, such as SO(d). Since this approach assumes that data lies on a subspace that is homeomorphic to the Lie group itself, we here investigate how this assumption holds in the context of images that are generated by projecting a d-dimensional volume with unknown pose in SO(d). Upon examining different theoretical candidates for the group and image space, we show that the attempt to define a group action on the data space generally fails, as it requires more specific geometric constraints on the volume. Using geometric VAEs, our experiments confirm that this constraint is key to proper pose inference, and we discuss the potential of these results for applications and future work.","PeriodicalId":72637,"journal":{"name":"Colloques sur le traitement du signal et des images","volume":"5 1","pages":"329-332"},"PeriodicalIF":0.0,"publicationDate":"2022-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79677521","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}
引用次数: 0
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整，为了账户安全，请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们：info@booksci.cn Book学术提供免费学术资源搜索服务，方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号：481959085
Book学术官方微信