检索结果-内蒙古大学图书馆

MPCNet: Improved MeshSegNet Based on Position Encoding and Channel Attention

IEEE ACCESS 2023年 11卷 23326-23334页

作者： Hu, Hanqing Li, Zhengxun Gao, Weichao Beijing Informat Sci & Technol Univ Sch Econ & Management Beijing 100192 Peoples R China Beijing Key Lab Big Data Decis Making Green Dev Beijing 100192 Peoples R China

In the process of orthodontic treatment, it is a very important step to accurately segment each tooth and jaw model with computer assistance. The use of deep learning technology methods for tooth segmentation can not only save a lot of manual interaction and time cost but also improve the treatment effect. 3d tooth segmentation is a hot topic of interest for international related scholars, and some end-to-end tooth segmentation methods based on dental mesh scanning models have been emerging in recent years. due to the limited variety of existing models, they are not well suited for different 3d segmentation scenarios, and the feature extraction capability and segmentation effect of these models still need to be improved. In this paper, we propose a novel end-to-end tooth segmentation method, MPCNet, which adds multi-scale mesh density information to the input layer, uses position encoding and channel attention mechanism to improve MeshSegNet, and uses graph-cut post-processing to perform 3d tooth segmentation in real scenes. The effectiveness of MPCNet is evaluated on a real 3d scanned tooth segmentation dataset, which significantly outperforms the current mainstream segmentation methods.

关键词： Teeth Feature extraction Three-dimensional displays dentistry data mining Solid modeling deep learning semantic segmentation Orthodontics Tooth segmentation 3d deep learning virtual orthodontics 3d semantic segmentation attention mechanism

来源：评论

学校读者我要写书评

暂无评论

OctFormer: Octree-based Transformers for 3d Point Clouds

引用

ACM TRANSACTIONS ON GRAPHICS 2023年第4期42卷 1-11页

作者： Wang, Peng-Shuai Peking Univ Beijing Peoples R China

We propose octree-based transformers, named OctFormer, for 3d point cloud learning. OctFormer can not only serve as a general and effective backbone for 3d point cloud segmentation and object detection but also have linear complexity and is scalable for large-scale point clouds. The key challenge in applying transformers to point clouds is reducing the quadratic, thus overwhelming, computation complexity of attentions. To combat this issue, several works divide point clouds into non-overlapping windows and constrain attentions in each local window. However, the point number in each window varies greatly, impeding the efficient execution on GPU. Observing that attentions are robust to the shapes of local windows, we propose a novel octree attention, which leverages sorted shuffled keys of octrees to partition point clouds into local windows containing a fixed number of points while permitting shapes of windows to change freely. Andwe also introduce dilated octree attention to expand the receptive field further. Our octree attention can be implemented in 10 lines of code with open-sourced libraries and runs 17 times faster than other point cloud attentions when the point number exceeds 200... Built upon the octree attention, OctFormer can be easily scaled up and achieves state-of-the-art performances on a series of 3d semantic segmentation and 3d object detection benchmarks, surpassing previous sparse-voxel-based CNNs and point cloud transformers in terms of both efficiency and effectiveness. Notably, on the challenging ScanNet200 dataset, OctFormer outperforms sparse-voxel-based CNNs by 7.3 in mIoU. Our code and trained models are available at https:// wang- ***/ octformer.

关键词： Point Clouds Transformers Octree 3d semantic segmentation 3d Object detection

来源：评论

学校读者我要写书评

暂无评论

VoxelScape: Large Scale Simulated 3d Point Cloud dataset of Urban Traffic Environments

引用

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS 2023年第9期24卷 9435-9448页

作者： Saleh, Khaled Hossny, Mohammed Abobakr, Ahmed Attia, Mohammed Iskander, Julie Univ Newcastle Sch Informat & Phys Sci Callaghan NSW 2308 Australia Univ New South Wales Sch Engn & IT Sydney NSW 2052 Australia Cairo Univ Fac Comp & Artificial Intelligence Giza 2613 Egypt Alexandria Univ Med Res Inst Alexandria 5424041 Egypt Walter & Eliza Hall Inst Med Res Parkville Vic 3052 Australia

Having a profound understanding of the surrounding environment is considered one of the crucial tasks for the reliable operation of future self-driving cars. Light detection and Ranging (LidAR) sensor plays a critical role in achieving such understanding due to its capability to perceive the world in 3d. Similar to 2d perception tasks, current state-of-the-art methods in 3d perception tasks rely on deep neural networks (dNNs). However, the performance of 3d perception tasks, specially point-wise semantic segmentation, is not on par with their 2d counterparts. One of the main reasons is the lack of publicly available labelled 3d point cloud datasets (PCds) from 3d LidAR sensors. In this work, we are introducing the VoxelScape dataset, a large-scale simulated 3d PCd with 100K annotated point cloud scans. The annotations in the VoxelScape dataset include both point-wise semantic labels and 3d bounding box labels. Additionally, we used a number of baseline approaches to validate the transferability of VoxelScape to real 3d PCd for two challenging 3d perception tasks. The promising results have shown that training dNNs on VoxelScape boosted the performance of the 3d perception tasks on the real PCd. Furthermore, we are also releasing the proposed data generation pipeline for the research community to facilitate realistic simulation of 3d LidAR point cloud data for different scenarios beyond those covered in our VoxelScape dataset. The VoxelScape dataset and the corresponding LidAR simulation codes are publicly available at https://***/dataset

关键词： Three-dimensional displays Laser radar Annotations Sensors Task analysis semantics Point cloud compression Light detection and Ranging (LidAR) simulation 3d object detection 3d semantic segmentation annotations

来源：评论

学校读者我要写书评

暂无评论

Robust detection, segmentation, and Metrology of High Bandwidth Memory 3d Scans Using an Improved Semi-Supervised deep Learning Approach

引用

SENSORS 2023年第12期23卷 5470-5470页

作者： Wang, Jie Chang, Richard Zhao, Ziyuan Pahwa, Ramanpreet Singh ASTAR Inst Infocomm Res I2R 1 Fusionopolis Way21-01Connexis South Tower Singapore 138632 Singapore

Recent advancements in 3d deep learning have led to significant progress in improving accuracy and reducing processing time, with applications spanning various domains such as medical imaging, robotics, and autonomous vehicle navigation for identifying and segmenting different structures. In this study, we employ the latest developments in 3d semi-supervised learning to create cutting-edge models for the 3d object detection and segmentation of buried structures in high-resolution X-ray semiconductors scans. We illustrate our approach to locating the region of interest of the structures, their individual components, and their void defects. We showcase how semi-supervised learning is utilized to capitalize on the vast amounts of available unlabeled data to enhance both detection and segmentation performance. Additionally, we explore the benefit of contrastive learning in the data pre-selection step for our detection model and multi-scale Mean Teacher training paradigm in 3d semantic segmentation to achieve better performance compared with the state of the art. Our extensive experiments have shown that our method achieves competitive performance and is able to outperform by up to 16% on object detection and 7.8% on semantic segmentation. Additionally, our automated metrology package shows a mean error of less than 2 mu m for key features such as Bond Line Thickness and pad misalignment.

关键词： 3d semi-supervised Learning 3d object detection 3d semantic segmentation contrastive learning 3d metrology

来源：评论

学校读者我要写书评

暂无评论

Semi-automated dataset creation for semantic and instance segmentation of industrial point clouds.

引用

COMPUTERS IN INdUSTRY 2024年 155卷

作者： Birkeland, August Asheim Udnaes, Marius Norwegian Univ Sci & Technol Dept Comp Sci Sem Saelands Vei 9 N-7034 Trondheim Norway Cognite AS Oksenoyveien 10 N-1366 Lysaker Norway

The current practice for creating as-built geometric digital Twins (gdTs) of industrial facilities is both labour-intensive and error-prone. In aged industries it typically involves manually crafting a CAd or BIM model from a point cloud collected using terrestrial laser scanners. Recent advances within deep learning (dL) offer the possibility to automate semantic and instance segmentation of point clouds, contributing to a more efficient modelling process. dL networks, however, are data-intensive, requiring large domain-specific datasets. Producing labelled point cloud datasets involves considerable manual labour, and in the industrial domain no open-source instance segmentation dataset exists. We propose a semi-automatic workflow leveraging object descriptions contained in existing gdTs to efficiently create semantic-and instance-labelled point cloud datasets. To prove the efficiency of our workflow, we apply it to two separate areas of a gas processing plant covering a total of 40000 m2. We record the effort needed to process one of the areas, labelling a total of 260 million points in 70 h. When benchmarking on a state-of-the-art 3d instance segmentation network, the additional data from the 70-hour effort raises mIoU from 24.4% to 44.4%, AP from 19.7% to 52.5% and RC from 45.9% to 76.7% respectively.

关键词： Scan-to-BIM digital twin 3d semantic segmentation 3d instance segmentation Point cloud LidAR

来源：评论

学校读者我要写书评

暂无评论

NeiEA-NET: semantic segmentation of large-scale point cloud scene via neighbor enhancement and aggregation

引用

INTERNATIONAL JOURNAL OF APPLIEd EARTH OBSERVATION ANd GEOINFORMATION 2023年 119卷

作者： Xu, Yongyang Tang, Wei Zeng, Ziyin Wu, Weichao Wan, Jie Guo, Han Xie, Zhong China Univ Geosci Sch Comp Sci Wuhan Peoples R China State Key Lab Geoinformat Engn Xian 710054 Peoples R China Guangdong Hong Kong Macau Joint Lab Smart Cities Hong Kong 518000 Guangdong Peoples R China China Univ Geosci Key Lab geol & evaluat Minist Educ Wuhan Peoples R China Minist Nat Resources Key Lab Urban Land Resources Monitoring & Simulat Shenzhen 518034 Peoples R China

3d point cloud semantic segmentation is crucial for 3d environment perception and scene understanding, where learning of local context in point clouds is a crucial challenge. Existing approaches typically explore local context based on the predefined neighbors of point clouds. However, the widely used K-nearest neighbor algorithm (KNN) is far from optimal in defining local neighbors. In this study, we propose NeiEA-Net, a conceptually simple and effective network for point cloud semantic segmentation. The key to our approach is to optimize the local neighbors in 3d Euclidean space by taking full advantage of high-dimensional feature space as much as possible. In addition, we introduce a neighbor feature aggregation module to adaptively aggregate features with different scales in the local neighbors to further reduce the redundant information, thereby effectively learning the local details of point clouds. Experiments conducted on three large-scale benchmarks, S3dIS, Toronto3d and SensatUrban, demonstrate the superiority of our network.

关键词： Point cloud 3d semantic segmentation Large-scale scene KNN

来源：评论

学校读者我要写书评

暂无评论

GOV-NeSF: Generalizable Open-Vocabulary Neural semantic Fields

GOV-NeSF: Generalizable Open-Vocabulary Neural Semantic Fiel...

引用

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

作者： Wang, Yunsong Chen, Hanlin Lee, Gim Hee Natl Univ Singapore Dept Comp Sci Singapore Singapore

ISBN: (纸本)9798350353006

Recent advancements in vision-language foundation models have significantly enhanced open-vocabulary 3d scene understanding. However, the generalizability of existing methods is constrained due to their framework designs and their reliance on 3d data. We address this limitation by introducing Generalizable Open-Vocabulary Neural semantic Fields (GOV-NeSF), a novel approach offering a generalizable implicit representation of 3d scenes with open-vocabulary semantics. We aggregate the geometry-aware features using a cost volume, and propose a Multi-view Joint Fusion module to aggregate multi-view features through a cross-view attention mechanism, which effectively predicts view-specific blending weights for both colors and open-vocabulary features. Remarkably, our GOV-NeSF exhibits state-of-the-art performance in both 2d and 3d open-vocabulary semantic segmentation, eliminating the need for ground truth semantic labels or depth priors, and effectively generalize across scenes and datasets without fine-tuning.

关键词： 3d Scene Understanding 3d semantic segmentation Neural Radiance Fields Open-Vocabulary

来源：评论

学校读者我要写书评

暂无评论

Towards Large-scale 3d Representation Learning with Multi-dataset Point Prompt Training

Towards Large-scale 3D Representation Learning with Multi-da...

引用

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

作者： Wu, Xiaoyang Tian, Zhuotao Wen, Xin Peng, Bohao Liu, Xihui Yu, Kaicheng Zhao, Hengshuang Univ Hong Kong Hong Kong Peoples R China Chinese Univ Hong Kong Hong Kong Peoples R China Westlake Univ Hangzhou Peoples R China Alibaba Grp Hangzhou Peoples R China

ISBN: (纸本)9798350353006

The rapid advancement of deep learning models is often attributed to their ability to leverage massive training data. In contrast, such privilege has not yet fully benefited 3d deep learning, mainly due to the limited availability of large-scale 3d datasets. Merging multiple available data sources and letting them collaboratively train a single model is a potential solution. However, due to the large domain gap between 3d point cloud datasets, such mixed supervision could adversely affect the model's performance and lead to degenerated performance (i.e., negative transfer) compared to single-dataset training. In view of this challenge, we introduce Point Prompt Training (PPT), a novel framework for multi-dataset synergistic learning in the context of 3d representation learning that supports multiple pre-training paradigms. Based on this framework, we propose Prompt-driven Normalization, which adapts the model to different datasets with domain-specific prompts and Language-guided Categorical Alignment that decently unifies the multiple-dataset label spaces by leveraging the relationship between label text. Extensive experiments verify that PPT can overcome the negative transfer associated with synergistic learning and produce generalizable representations. Notably, it achieves state-of-the-art performance on each dataset using a single weight-shared model with supervised multi-dataset training. Moreover, when served as a pre-training framework, it outperforms other pre-training approaches regarding representation quality and attains remarkable state-of-the-art performance across over ten diverse downstream tasks spanning both indoor and outdoor 3d scenarios.

关键词： 3d Pre-training 3d Representation Learning 3d semantic segmentation

来源：评论

学校读者我要写书评

暂无评论

Point Transformer V3: Simpler, Faster, Stronger

Point Transformer V3: Simpler, Faster, Stronger

引用

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

作者： Wu, Xiaoyang Jiang, Li Wang, Peng-Shuai Liu, Zhijian Liu, Xihui Qiao, Yu Ouyang, Wanli He, Tong Zhao, Hengshuang HKU Hong Kong Peoples R China SH AI Lab Shanghai Peoples R China CUHK SZ Shenzhen Peoples R China PKU Beijing Peoples R China MIT Cambridge MA 02139 USA

ISBN: (纸本)9798350353013;9798350353006

This paper is not motivated to seek innovation within the attention mechanism. Instead, it focuses on overcoming the existing trade-offs between accuracy and efficiency within the context of point cloud processing, leveraging the power of scale. drawing inspiration from recent advances in 3d large-scale representation learning, we recognize that model performance is more influenced by scale than by intricate design. Therefore, we present Point Transformer V3 (PTv3), which prioritizes simplicity and efficiency over the accuracy of certain mechanisms that are minor to the overall performance after scaling, such as replacing the precise neighbor search by KNN with an efficient serialized neighbor mapping of point clouds organized with specific patterns. This principle enables significant scaling, expanding the receptive field from 16 to 1024 points while remaining efficient (a 3x increase in processing speed and a 10x improvement in memory efficiency compared with its predecessor, PTv2). PTv3 attains state-of-the-art results on over 20 downstream tasks that span both indoor and outdoor scenarios. Further enhanced with multi-dataset joint training, PTv3 pushes these results to a higher level.

关键词： 3d Backbone 3d Object detection 3d semantic segmentation

来源：评论

学校读者我要写书评

暂无评论

Multi-Space Alignments Towards Universal LidAR segmentation

Multi-Space Alignments Towards Universal LiDAR Segmentation

引用

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

作者： Liu, Youquan Kong, Lingdong Wu, Xiaoyang Chen, Runnan Li, Xin Pane, Liang Liu, Ziwei Ma, Yuexin ShanghaiTech Univ Shanghai Peoples R China Shanghai AI Lab Shanghai Peoples R China Natl Univ Singapore Singapore Singapore Univ Hong Kong Hong Kong Peoples R China East China Normal Univ Shanghai Peoples R China Nanyang Technol Univ S Lab Singapore Singapore

ISBN: (纸本)9798350353006

A unified and versatile LidAR segmentation model with strong robustness and generalizability is desirable for safe autonomous driving perception. This work presents M3Net, a one-of-a-kind framework for fulfilling multi-task, multidataset, multi-modality LidAR segmentation in a universal manner using just a single set of parameters. To better exploit data volume and diversity, we first combine largescale driving datasets acquired by different types of sensors from diverse scenes and then conduct alignments in three spaces, namely data, feature, and label spaces, during the training. As a result, M3Net is capable of taming heterogeneous data for training state-of-the-art LidAR segmentation models. Extensive experiments on twelve LidAR segmentation datasets verify our effectiveness. Notably, using a shared set of parameters, M3Net achieves 75.1%, 83.1%, and 72.4% mIoU scores, respectively, on the official benchmarks of semanticKITTI, nuScenes, and Waymo Open.

关键词： 3d semantic segmentation Autonomous driving LidAR segmentation Multi-dataset Training

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：