检索结果-内蒙古大学图书馆

International conference on Computer Graphics, visualization, Computer Vision and Image Processing 2021, CGVCVIP 2021, Connected Smart Cities 2021, CSC 2021 and Big data Analytics, data Mining and Computational Intelligence 2021, BIGdACI 2021 - Held at the 15th Multi-conference on Computer Science and Information Systems, MCCSIS 2021

作者： ding, Yueming Mok, P.Y. The Hong Kong Polytechnic University Inst. Textiles and Clothing Hong Kong Laboratory for Artificial Intelligence in Design Hong Kong

ISBN: (纸本)9789898704320

3d face reconstruction from 2d images is an important research topic because it supports a wide range of applications, such as face recognition, animations, games, and AR/VR systems. 3d face reconstruction from contour features is a challenging task, because traditional edge detection algorithms produce a lot of noises, which are prone to making the reconstruction model trapped in a local optimum or even being degraded. With the development of deep learning, a lot of researcher introduce neural network into contour detection, which can extract relatively clear contours compared with previous methods. In this article, we employ a hard blended face contour feature from neural network and canny edge extractor for face reconstruction. Our method not only improves the 3d face model reconstruction accuracy on synthesis images, but performs more accurately and robustly on in-the-wild images under blurriness, makeup, occlusion and ill-illumination conditions. © 2021 International conference on Computer Graphics, visualization, Computer Vision and Image Processing 2021, CGVCVIP 2021, Connected Smart Cities 2021, CSC 2021 and Big data Analytics, data Mining and Computational Intelligence 2021, BIGdACI 2021 - Held at the 15th Multi-conference on Computer Science and Information Systems, MCCSIS 2021. All rights reserved.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

deep Active Surface Models

Deep Active Surface Models

引用

IEEE/CVF conference on Computer Vision and Pattern Recognition (CVPR)

作者： Wickramasinghe, Udaranga Fua, Pascal Knott, Graham Ecole Polytech Fed Lausanne Comp Vis Lab Lausanne Switzerland Ecole Polytech Fed Lausanne BioEM Lab Lausanne Switzerland

ISBN: (纸本)9781665445092

Active Surface Models have a long history of being useful to model complex 3d surfaces. But only Active Contours have been used in conjunction with deep networks, and then only to produce the data term as well as meta-parameter maps controlling them. In this paper, we advocate a much tighter integration. We introduce layers that implement them that can be integrated seamlessly into Graph Convolutional Networks to enforce sophisticated smoothness priors at an acceptable computational cost. We will show that the resulting deep Active Surface Models outperform equivalent architectures that use traditional regularization loss terms to impose smoothness priors for 3d surface reconstruction from 2d images and for 3d volume segmentation.

关键词： Measurement Surface reconstruction Solid modeling Image segmentation Three-dimensional displays Smoothing methods Computational modeling

来源：评论

学校读者我要写书评

暂无评论

A Large-Scale Indoor Layout reconstruction and Localization System for Spatial-Aware Mobile AR Applications 4

A Large-Scale Indoor Layout Reconstruction and Localization ...

引用

4th IEEE International conference on Artificial Intelligence and virtual Reality (AIVR)

作者： Hsiao, Kai-Wen Su, Jheng-Wei Hung, Yu-Chih Chen, Kuo-Wei Yao, Chih-Yuan Chu, Hung-Kuo Natl Tsing Hua Univ Comp Sci Hsinchu Taiwan Natl Taiwan Univ Sci & Technol Comp Sci & Informat Engn Taipei Taiwan

ISBN: (纸本)9781665432252

Augmented reality (AR) has renewed the perspective of how people see and process information in daily life by blending the real world with rich and interactive virtual contents. However, restricted by the limited computation resources of mobile devices, most existing AR applications can process only local features in front of the camera. Such limitation severely hinders the progress of inventing more practical AR applications that demand more complex interaction. To break this barrier, we introduce a novel spatial-aware AR application framework for the indoor environment in this work. The core techniques include a large-scale indoor layout reconstruction system that can reconstruct the 3d layout of an entire floor plan from few panoramas taken via commodity cameras, and an online localization system that can accurately align the virtual 3d layout with real world environment in real time. By incorporating the perception of global scene structure with the AR interaction pipeline, our system can support more sophisticated applications with the complex interplay among the users, virtual objects and the real world scene. We tested our framework on a large-scale indoor environment and demonstrate its effectiveness on practical AR applications, a first-person-shooting game and an indoor navigation.

关键词： augmented reality indoor layout reconstruction mobile application neural network panoramic image

来源：评论

学校读者我要写书评

暂无评论

Into 3d-Reconstructed Apparel over virtual Try-On with virtual Reality

Into 3D-Reconstructed Apparel over Virtual Try-On with Virtu...

引用

IEEE International conference on Consumer Electronics-Taiwan (ICCE-TW)

作者： Surasachai doungtap Jirayu Petchhan Varinya Phanichraksaphong Jenq-Haur Wang International Graduate Program of Electrical Engineering and Computer Science Dept. of Electrical Engineering National Taiwan University of Science & Technology Taiwan R. O. C. Department of Computer Science and Information Engineering National Taipei University of Technology Taiwan R. O. C.

virtualization technologies are still growing bigger and faster. despite the greatness of its advancement, the costume industry is still very accessible when it comes to real trials. Off-the-shelf stuff are inadequate details for the desired individual to assess its in-depth utility for each garment trying on for a second, including custom stuff are much harder to try out right away. To this end, 2d image-based 3d reconstruction inclusive of touchable-virtualized space is accessible easier to stuff details for mans' decision making in purchasing. We establish the overall end-to-end pipeline from reconstruction until visualization for one instance to be triable on its stuff for a moment. As an expectation, our proposed approach can bring objects into the experimental area and use them immediately without any obstacle.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Volumetric disentanglement for 3d Scene Manipulation

Volumetric Disentanglement for 3D Scene Manipulation

引用

IEEE Workshop on Applications of Computer Vision (WACV)

作者： Sagie Benaim Frederik Warburg Peter Ebert Christensen Serge Belongie University of Copenhagen Technical University of Denmark

Recently, advances in differential volumetric rendering enabled significant breakthroughs in the photo-realistic and fine-detailed reconstruction of complex 3d scenes, which is key for many virtual reality applications. However, in the context of augmented reality, one may also wish to effect semantic manipulations or augmentations of objects within a scene. To this end, we propose a volumetric framework for (i) disentangling or separating, the volumetric representation of a given foreground object from the background, and (ii) semantically manipulating the foreground object, as well as the background. Our framework takes as input a set of 2d masks specifying the desired foreground object for training views, together with the associated 2d views and poses, and produces a foreground-background disentanglement that respects the surrounding illumination, reflections, and partial occlusions, which can be applied to both training and novel views. Our method enables the separate control of pixel color and depth as well as 3d similarity transformations of both the foreground and background objects. We subsequently demonstrate our framework’s applicability on several downstream manipulation tasks, going beyond the placement and movement of foreground objects. These tasks include object camouflage, non-negative 3d object in-painting, 3d object translation, 3d object inpainting, and 3d text-based object manipulation. The project webpage is provided in https://***/volumetric-disentanglement/.

关键词：

来源：评论

学校读者我要写书评

暂无评论

VoxelCache: Accelerating Online Mapping in Robotics and 3d reconstruction Tasks 22

VoxelCache: Accelerating Online Mapping in Robotics and 3D R...

引用

Proceedings of the International conference on Parallel architectures and Compilation Techniques

作者： Sankeerth durvasula Raymond Kiguru Samarth Mathur Jenny Xu Jimmy Lin Nandita Vijaykumar University of Toronto PES Institute of Technology

ISBN: (纸本)9781450398688

Real-time 3d mapping is a critical component in many important applications today including robotics, AR/VR, and 3d visualization. 3d mapping involves continuously fusing depth maps obtained from depth sensors in phones, robots, and autonomous vehicles into a single 3d representative model of the scene. Many important applications, e.g., global path planning and trajectory generation in micro aerial vehicles, require the construction of large maps at high resolutions. In this work, we identify mapping, i.e., construction and updates of 3d maps to be a critical bottleneck in these applications. The memory required and access times of these maps limit the size of the environment and the resolution with which the environment can be feasibly mapped, especially in resource constrained environments such as autonomous robot platforms and portable devices. To address this challenge, we propose VoxelCache: a hardware-software technique to accelerate map data access times in 3d mapping applications. We observe that mapping applications typically access voxels in the map that are spatially co-located to each other. We leverage this temporal locality in voxel accesses to cache indices to blocks of voxels to enable quick lookup and avoid expensive access times. We evaluate VoxelCache on popularly used mapping and reconstruction applications on both GPUs and CPUs. We demonstrate an average speedup of 1.47X (up to 1.66X) and 1.79X (up to 1.91X) on CPUs and GPUs respectively.

关键词： hardware acceleration mapping reconstruction caching SLAM

来源：评论

学校读者我要写书评

暂无评论

digital Historical Pavia: 3d Modeling in Educational Context for Cultural Heritage Promotion 3rd

Digital Historical Pavia: 3D Modeling in Educational Contex...

引用

3rd Florence Heri-Tech International conference, Florence Heri-Tech 2022

作者： Cantoni, Virginio dondi, Piercarlo Gullotti, Alessio Lombardi, Luca Mosconi, Mauro Nour, Roberto Setti, Alessandra Department of Electrical Computer and Biomedical Engineering University of Pavia Via A. Ferrata 5 Pavia27100 Italy

ISBN: (纸本)9783031203015

The "digital Historical Pavia" project aims to prove the value of digital media technologies for enhancing promotion and accessibility of Cultural Heritage, while teaching students the basics of computer graphics. It integrates technology into attractive and meaningful presentations of local cultural assets of the 14 th – 16 th century when the city of Pavia experienced several transformations. This paper summarizes the main results of the project showing the outcomes of three case studies: (i) the setup of an educational and experiential room for the exhibition "1525–2015. Pavia, the Battle, the Future. Nothing was the same again";(ii) the virtual reconstruction of the city of Pavia in the Renaissance, including a timelapse of the urban evolution of the city during the 16 th century;(iii) the 3d modeling of the Ark of St. Augustine, a complex funerary monument of the second half of the 14 th century, and the development of a related online serious game. All the 3d models were created by students of the master’s degree in Computer Engineering of the University of Pavia, showing the potentiality of an experiential learning approach for teaching computer science and computer graphics concepts. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： 3d modeling

来源：评论

学校读者我要写书评

暂无评论

Fifteenth International conference on Quality Control by Artificial Vision

Fifteenth International Conference on Quality Control by Art...

引用

15th International conference on Quality Control by Artificial Vision

ISBN: (纸本)9781510644267

The proceedings contain 50 papers. The topics discussed include: aperture localization based on vibro-stimuli generated from distance variation;training PointNet for human point cloud segmentation with 3d meshes;development of a 3d visualization system for the cerebral aneurysm coil embolization;3d reconstruction of mirror-like surfaces by smart deflectometry;quality assessment of dynamic virtual relighting from RTI data: application to the inspection of engineering surfaces;tiny range image sensors using multiple laser lights for short distance measurement;development of image simulator for forward-looking sonar using 3d rendering;separation of compound actions with wrist and finger based on EMG;and latent space visualization of half face and full face by generative model.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Embracing Radiance Field Rendering in 6G: Over-the-Air Training and Inference with 3d Contents

arXiv

引用

arXiv 2024年

作者： Wu, Guanlin Lyu, Zhonghao Zhang, Juyong Xu, Jie Guangdong518172 China The School of Mathematical Science University of Science and Technology of China Hefei230026 China

The efficient representation, transmission, and reconstruction of three-dimensional (3d) contents are becoming increasingly important for sixth-generation (6G) networks that aim to merge virtual and physical worlds for offering immersive communication experiences. Neural radiance field (NeRF) and 3d Gaussian splatting (3d-GS) have recently emerged as two promising 3d representation techniques based on radiance field rendering, which are able to provide photorealistic rendering results for complex scenes. Therefore, embracing NeRF and 3d-GS in 6G networks is envisioned to be a prominent solution to support emerging 3d applications with enhanced quality of experience. This paper provides a comprehensive overview on the integration of NeRF and 3d-GS in 6G. First, we review the basics of the radiance field rendering techniques, and highlight their applications and implementation challenges over wireless networks. Next, we consider the over-the-air training of NeRF and 3d-GS models over wireless networks by presenting various learning techniques. We particularly focus on the federated learning design over a hierarchical device-edge-cloud architecture, which is suitable for exploiting distributed data and computing resources over 6G networks to train large models representing large-scale scenes. Then, we consider the over-the-air rendering of NeRF and 3d-GS models at wireless network edge. We present three practical rendering architectures, namely local, remote, and co-rendering, respectively, and provide model compression approaches to facilitate the transmission of radiance field models for rendering. We also present rendering acceleration approaches and joint computation and communication designs to enhance the rendering efficiency. In a case study, we propose a new semantic communication enabled 3d content transmission design, in which the radiance field models are exploited as the semantic knowledge base to reduce the communication overhead for distributed inference.

关键词： Wireless networks

来源：评论

学校读者我要写书评

暂无评论

OralViewer: 3d demonstration of dental Surgeries for Patient Education with Oral Cavity reconstruction from a 2d Panoramic X-ray 21

OralViewer: 3D Demonstration of Dental Surgeries for Patient...

引用

26th International conference on Intelligent User Interfaces (IUI)

作者： Liang, Yuan Qiu, Liang Lu, Tiancheng Fang, Zhujun Tu, dezhan Yang, Jiawei Shao, Yiting Wang, Kun Chen, Xiang Anthony He, Lei Univ Calif Los Angeles Los Angeles CA 90095 USA Univ Pittsburgh Pittsburgh PA 15260 USA

ISBN: (纸本)9781450380171

Patient's understanding on forthcoming dental surgeries is required by patient-centered care and helps reduce anxiety. due to the complexity of dental surgeries and the patient-dentist expertise gap, conventional techniques of patient education are usually not effective for explaining surgical steps. In this paper, we present OralViewer-the first interactive application that enables dentist's demonstration of dental surgeries in 3d to promote patients' understanding. OralViewer takes a single 2d panoramic dental X-ray to reconstruct patient-specific 3d teeth structures, which are then assembled with registered gum and jaw bone models for complete oral cavity modeling. during the demonstration, OralViewer enables dentists to show surgery steps with virtual dental instruments that can animate effects on a 3d model in real-time. A technical evaluation shows that our deep learning model achieves a mean Intersection over Union (IoU) of 0.771 for 3d teeth reconstruction. A patient study with 12 participants shows OralViewer can improve patients' understanding of surgeries. A preliminary expert study with 3 board-certified dentists further verifies the clinical validity of our system.

关键词： deep learning 3d visualization patient education

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：