发布求助
文献互助 智能选刊 最新文献

Proceedings. International Conference on 3D Vision最新文献

筛选
英文 中文
SocialGen: Modeling Multi-Human Social Interaction with Language Models. SocialGen：用语言模型建模多人社交互动。
Proceedings. International Conference on 3D Vision Pub Date : 2026-03-01 Epub Date: 2026-05-27 DOI: 10.1109/3dv69130.2026.00175
Heng Yu, Juze Zhang, Changan Chen, Tiange Xiang, Yusu Fang, Juan Carlos Niebles, Ehsan Adeli
{"title":"SocialGen: Modeling Multi-Human Social Interaction with Language Models.","authors":"Heng Yu, Juze Zhang, Changan Chen, Tiange Xiang, Yusu Fang, Juan Carlos Niebles, Ehsan Adeli","doi":"10.1109/3dv69130.2026.00175","DOIUrl":"10.1109/3dv69130.2026.00175","url":null,"abstract":"<p><p>Human interactions in everyday life are inherently social, involving engagements with diverse individuals across various contexts. Modeling these social interactions is fundamental to a wide range of real-world applications. In this paper, we introduce SocialGen, the first unified motion-language model capable of modeling interaction behaviors among varying numbers of individuals, to address this crucial yet challenging problem. Unlike prior methods that are limited to two-person interactions, we propose a novel social motion representation that supports tokenizing the motions of an arbitrary number of individuals and aligning them with the language space. This alignment enables the model to leverage rich, pretrained linguistic knowledge to better understand and reason about human social behaviors. To tackle the challenges of data scarcity, we curate a comprehensive multi-human interaction dataset, <b>SocialX</b>, enriched with textual annotations. Leveraging this dataset, we establish the first comprehensive benchmark for multi-human interaction tasks. Our method achieves state-of-the-art performance across motion-language tasks, setting a new standard for multi-human interaction modeling. Project page: socialgenx.github.io.</p>","PeriodicalId":91162,"journal":{"name":"Proceedings. International Conference on 3D Vision","volume":"2026 ","pages":"1844-1860"},"PeriodicalIF":0.0,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13218778/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148140244","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
Message from the Program Chairs: 3DV 2022 节目主持人的信息:3DV 2022
Proceedings. International Conference on 3D Vision Pub Date : 2022-09-01 DOI: 10.1109/3dv57658.2022.00006
Angela Dai, J. Kosecka, Gin Hee Lee, K. Schindler
{"title":"Message from the Program Chairs: 3DV 2022","authors":"Angela Dai, J. Kosecka, Gin Hee Lee, K. Schindler","doi":"10.1109/3dv57658.2022.00006","DOIUrl":"https://doi.org/10.1109/3dv57658.2022.00006","url":null,"abstract":"","PeriodicalId":91162,"journal":{"name":"Proceedings. International Conference on 3D Vision","volume":"88 1","pages":"1"},"PeriodicalIF":0.0,"publicationDate":"2022-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78708115","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
Message from the 3DV 2020 Program Chairs 来自3DV 2020项目主席的信息
Proceedings. International Conference on 3D Vision Pub Date : 2020-10-01 DOI: 10.1109/ldav51489.2020.00005
A. Hilton, Z. Kukelova, Stephen Lin, J. Sato
{"title":"Message from the 3DV 2020 Program Chairs","authors":"A. Hilton, Z. Kukelova, Stephen Lin, J. Sato","doi":"10.1109/ldav51489.2020.00005","DOIUrl":"https://doi.org/10.1109/ldav51489.2020.00005","url":null,"abstract":"","PeriodicalId":91162,"journal":{"name":"Proceedings. International Conference on 3D Vision","volume":"1 1","pages":"xx"},"PeriodicalIF":0.0,"publicationDate":"2020-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79162892","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
SEGCloud: Semantic Segmentation of 3D Point Clouds SEGCloud: 3D点云的语义分割
Proceedings. International Conference on 3D Vision Pub Date : 2017-10-01 DOI: 10.1109/3DV.2017.00067
Lyne P. Tchapmi, C. Choy, Iro Armeni, JunYoung Gwak, S. Savarese
{"title":"SEGCloud: Semantic Segmentation of 3D Point Clouds","authors":"Lyne P. Tchapmi, C. Choy, Iro Armeni, JunYoung Gwak, S. Savarese","doi":"10.1109/3DV.2017.00067","DOIUrl":"https://doi.org/10.1109/3DV.2017.00067","url":null,"abstract":"3D semantic scene labeling is fundamental to agents operating in the real world. In particular, labeling raw 3D point sets from sensors provides fine-grained semantics. Recent works leverage the capabilities of Neural Networks (NNs), but are limited to coarse voxel predictions and do not explicitly enforce global consistency. We present SEGCloud, an end-to-end framework to obtain 3D point-level segmentation that combines the advantages of NNs, trilinear interpolation(TI) and fully connected Conditional Random Fields (FC-CRF). Coarse voxel predictions from a 3D Fully Convolutional NN are transferred back to the raw 3D points via trilinear interpolation. Then the FC-CRF enforces global consistency and provides fine-grained semantics on the points. We implement the latter as a differentiable Recurrent NN to allow joint optimization. We evaluate the framework on two indoor and two outdoor 3D datasets (NYU V2, S3DIS, KITTI, this http URL), and show performance comparable or superior to the state-of-the-art on all datasets.","PeriodicalId":91162,"journal":{"name":"Proceedings. International Conference on 3D Vision","volume":"43 1","pages":"537-547"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86432312","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: 628
Performance Evaluation of 3D Correspondence Grouping Algorithms 三维对应分组算法的性能评价
Proceedings. International Conference on 3D Vision Pub Date : 2017-10-01 DOI: 10.1109/3DV.2017.00060
Jiaqi Yang, Ke Xian, Yang Xiao, ZHIGUO CAO
{"title":"Performance Evaluation of 3D Correspondence Grouping Algorithms","authors":"Jiaqi Yang, Ke Xian, Yang Xiao, ZHIGUO CAO","doi":"10.1109/3DV.2017.00060","DOIUrl":"https://doi.org/10.1109/3DV.2017.00060","url":null,"abstract":"This paper presents a thorough evaluation of several widely-used 3D correspondence grouping algorithms, motived by their significance in vision tasks relying on correct feature correspondences. A good correspondence grouping algorithm is desired to retrieve as many as inliers from initial feature matches, giving a rise in both precision and recall. Towards this rule, we deploy the experiments on three benchmarks respectively addressing shape retrieval, 3D object recognition and point cloud registration scenarios. The variety in application context brings a rich category of nuisances including noise, varying point densities, clutter, occlusion and partial overlaps. It also results to different ratios of inliers and correspondence distributions for comprehensive evaluation. Based on the quantitative outcomes, we give a summarization of the merits/demerits of the evaluated algorithms from both performance and efficiency perspectives.","PeriodicalId":91162,"journal":{"name":"Proceedings. International Conference on 3D Vision","volume":"48 1","pages":"467-476"},"PeriodicalIF":0.0,"publicationDate":"2017-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82617045","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: 22
GSLAM: Initialization-Robust Monocular Visual SLAM via Global Structure-from-Motion GSLAM:初始化-基于全局结构-运动的鲁棒单目SLAM
Proceedings. International Conference on 3D Vision Pub Date : 2017-08-16 DOI: 10.1109/3DV.2017.00027
Chengzhou Tang, Oliver Wang, P. Tan
{"title":"GSLAM: Initialization-Robust Monocular Visual SLAM via Global Structure-from-Motion","authors":"Chengzhou Tang, Oliver Wang, P. Tan","doi":"10.1109/3DV.2017.00027","DOIUrl":"https://doi.org/10.1109/3DV.2017.00027","url":null,"abstract":"Many monocular visual SLAM algorithms are derived from incremental structure-from-motion (SfM) methods. This work proposes a novel monocular SLAM method which integrates recent advances made in global SfM. In particular, we present two main contributions to visual SLAM. First, we solve the visual odometry problem by a novel rank-1 matrix factorization technique which is more robust to the errors in map initialization. Second, we adopt a recent global SfM method for the pose-graph optimization, which leads to a multi-stage linear formulation and enables L1 optimization for better robustness to false loops. The combination of these two approaches generates more robust reconstruction and is significantly faster (4X) than recent state-of-the-art SLAM systems. We also present a new dataset recorded with ground truth camera motion in a Vicon motion capture room, and compare our method to prior systems on it and established benchmark datasets.","PeriodicalId":91162,"journal":{"name":"Proceedings. International Conference on 3D Vision","volume":"6 1","pages":"155-164"},"PeriodicalIF":0.0,"publicationDate":"2017-08-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82151666","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: 14
3D Face Hallucination from a Single Depth Frame. 单深度帧的3D面部幻觉。
Proceedings. International Conference on 3D Vision Pub Date : 2014-12-01 DOI: 10.1109/3DV.2014.67
Shu Liang, Ira Kemelmacher-Shlizerman, Linda G Shapiro
{"title":"3D Face Hallucination from a Single Depth Frame.","authors":"Shu Liang,&nbsp;Ira Kemelmacher-Shlizerman,&nbsp;Linda G Shapiro","doi":"10.1109/3DV.2014.67","DOIUrl":"https://doi.org/10.1109/3DV.2014.67","url":null,"abstract":"<p><p>We present an algorithm that takes a single frame of a person's face from a depth camera, e.g., Kinect, and produces a high-resolution 3D mesh of the input face. We leverage a dataset of 3D face meshes of 1204 distinct individuals ranging from age 3 to 40, captured in a neutral expression. We divide the input depth frame into semantically significant regions (eyes, nose, mouth, cheeks) and search the database for the best matching shape per region. We further combine the input depth frame with the matched database shapes into a single mesh that results in a highresolution shape of the input person. Our system is fully automatic and uses only depth data for matching, making it invariant to imaging conditions. We evaluate our results using ground truth shapes, as well as compare to state-of-the-art shape estimation methods. We demonstrate the robustness of our local matching approach with high-quality reconstruction of faces that fall outside of the dataset span, e.g., faces older than 40 years old, facial expressions, and different ethnicities.</p>","PeriodicalId":91162,"journal":{"name":"Proceedings. International Conference on 3D Vision","volume":"2014 ","pages":"31-38"},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1109/3DV.2014.67","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"33994948","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: 24
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：604180095
Book学术官方微信
小红书