2020 International Conference on 3D Immersion (IC3D)最新文献_第2页

Stereoscopic Dataset from A Video Game: Detecting Converged Axes and Perspective Distortions in S3D Videos 来自视频游戏的立体数据集:在S3D视频中检测聚合轴和透视扭曲

2020 International Conference on 3D Immersion (IC3D) Pub Date : 2020-12-15 DOI: 10.1109/IC3D51119.2020.9376375

K. Malyshev, S. Lavrushkin, D. Vatolin

引用次数: 1

Machine Perception Point Cloud Quality Assessment Via Vision Tasks 基于视觉任务的机器感知点云质量评估

2020 International Conference on 3D Immersion (IC3D) Pub Date : 2020-12-15 DOI: 10.1109/IC3D51119.2020.9376344

Jiapeng Lu, Linyao Gao, Wenjie Zhu, Yiling Xu

{"title":"Machine Perception Point Cloud Quality Assessment Via Vision Tasks","authors":"Jiapeng Lu, Linyao Gao, Wenjie Zhu, Yiling Xu","doi":"10.1109/IC3D51119.2020.9376344","DOIUrl":"https://doi.org/10.1109/IC3D51119.2020.9376344","url":null,"abstract":"LiDAR sensing is a newly developed 3D acquisition technology which is widely applied in auto-driving area. Different from the human perception point cloud, the generated 3D data is machine perception point clouds which are designed for specific vision tasks in realistic life, such as point cloud detection, segmentation and recognition. Therefore, instead of traditional subjective quality estimation, the quality assessment of machine perception point cloud is a new challenge. In this paper, we propose a machine perception point cloud quality assessment via various vision tasks, evaluating the point cloud quality based on the performance in vision tasks of different level of distorted point cloud. Firstly, we utilize the state-of-the-art point cloud compression algorithm to obtain the distorted point cloud. Then, we explore the potentials of distorted point clouds in detection and segmentation precision, comparing the results in different testing conditions. Finally, we propose the machine perception ROI based point cloud compression framework achieves notable performance on vision tasks result while do insignificant influence on PSNR.The experimental results illustrate the correspondence between point cloud quality and the performance in vision tasks, verifying the effectiveness of the proposed method.","PeriodicalId":159318,"journal":{"name":"2020 International Conference on 3D Immersion (IC3D)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131946665","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: 1

The Implications of Interpupillary Distance Variability for Virtual Reality 瞳孔间距变化对虚拟现实的影响

2020 International Conference on 3D Immersion (IC3D) Pub Date : 2020-12-15 DOI: 10.1109/IC3D51119.2020.9376369

P. Hibbard, L. Dam, P. Scarfe

引用次数: 12

Toward Texturing for Immersive Modeling of Environment Reconstructed from 360 Multi-Camera 360多摄像机重建环境沉浸式建模的纹理化研究

2020 International Conference on 3D Immersion (IC3D) Pub Date : 2020-12-15 DOI: 10.1109/IC3D51119.2020.9376323

M. Lhuillier

引用次数: 0

VST3D-Net:Video-Based Spatio-Temporal Network for 3D Shape Reconstruction from a Video VST3D-Net:基于视频的三维形状重构时空网络

2020 International Conference on 3D Immersion (IC3D) Pub Date : 2020-12-15 DOI: 10.1109/IC3D51119.2020.9376350

Jinglun Yang, Guanglun Zhang, Youhua Li, Lu Yang

{"title":"VST3D-Net:Video-Based Spatio-Temporal Network for 3D Shape Reconstruction from a Video","authors":"Jinglun Yang, Guanglun Zhang, Youhua Li, Lu Yang","doi":"10.1109/IC3D51119.2020.9376350","DOIUrl":"https://doi.org/10.1109/IC3D51119.2020.9376350","url":null,"abstract":"In this paper, we propose the Video-based Spatio-Temporal 3D Network (VST3D-Net), which is a novel learning approach of viewpoint-invariant 3D shape reconstruction from monocular video. In our VST3D-Net, a spatial feature extraction subnetwork is designed to encode the local and global spatial relationships of the object in the image. The extracted latent spatial features have implicitly embedded both shape and pose information. Although a single view can also be used to recover a 3D shape, more rich shape information of the dynamic object can be explored and leveraged from video frames. To generate the viewpoint-free 3D shape, we design a temporal correlation feature extractor. It handles the temporal consistency of the shape and pose of the moving object simultaneously. Therefore, both the canonical 3D shape and the corresponding pose at different frame are recovered by the network. We validate our approach on the ShapeNet-based video dataset and ApolloCar3D dataset. The experimental results show the proposed VST3D-Net can outperform the state-of-the-art approaches both in accuracy and efficiency.","PeriodicalId":159318,"journal":{"name":"2020 International Conference on 3D Immersion (IC3D)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129055965","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