SPNet: Deep 3D Object Classification and Retrieval Using Stereographic Projection

Yavartanoo, Mohsen; Kim, Eu Young; Lee, Kyoung Mu

doi:10.1007/978-3-030-20873-8_44

Cited by 43 publications

(29 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Over recent years, several DL approaches are emerging. In contrast to multiview-based [48][49][50][51][52] and voxel-based approaches [41,43,53,54], such approaches do not need specific pre-processing steps, and have been proved to provide state-of-the-art performances in semantic segmentation and classification task on standard benchmarks. Since the main objective of this work is to directly exploit the three-dimensionality of Point Clouds, a comprehensive overview of the multiview and voxel based methods is out of the scope, therefore only the point-based methods will be detailed.…”

Section: Semantic Segmentation Of Point Cloudsmentioning

confidence: 99%

Point Cloud Semantic Segmentation Using a Deep Learning Framework for Cultural Heritage

et al. 2020

View full text Add to dashboard Cite

In the Digital Cultural Heritage (DCH) domain, the semantic segmentation of 3D Point Clouds with Deep Learning (DL) techniques can help to recognize historical architectural elements, at an adequate level of detail, and thus speed up the process of modeling of historical buildings for developing BIM models from survey data, referred to as HBIM (Historical Building Information Modeling). In this paper, we propose a DL framework for Point Cloud segmentation, which employs an improved DGCNN (Dynamic Graph Convolutional Neural Network) by adding meaningful features such as normal and colour. The approach has been applied to a newly collected DCH Dataset which is publicy available: ArCH (Architectural Cultural Heritage) Dataset. This dataset comprises 11 labeled points clouds, derived from the union of several single scans or from the integration of the latter with photogrammetric surveys. The involved scenes are both indoor and outdoor, with churches, chapels, cloisters, porticoes and loggias covered by a variety of vaults and beared by many different types of columns. They belong to different historical periods and different styles, in order to make the dataset the least possible uniform and homogeneous (in the repetition of the architectural elements) and the results as general as possible. The experiments yield high accuracy, demonstrating the effectiveness and suitability of the proposed approach.

show abstract

Section: Semantic Segmentation Of Point Cloudsmentioning

confidence: 99%

Point Cloud Semantic Segmentation Using a Deep Learning Framework for Cultural Heritage

et al. 2020

View full text Add to dashboard Cite

show abstract

“…ModelNet10 Acc ModelNet40 Acc RotationNet [45] 98.46% 97.37% SPNet [46] 97.25% 92.63% SO-Net [18] 95,07% 93,40% Point2Sequence [47] 95,30% 92.60% Lonchanet [22] 94,37% -VFD 92.84% 88.74% binVoxNetPlus [48] 92.32% 85.47% Primitive-GAN [49] 92.20% 86.00% VSL [50] 91.00% 84.50% OrthographicNet [51] 88.56% -3DShapeNets [42] 83.50% 77.00% PointNet [43] 77,6% -…”

Section: Papermentioning

confidence: 99%

A Voxelized Fractal Descriptor for 3D Object Recognition

2020

View full text Add to dashboard Cite

Currently, state-of-the-art methods for 3D object recognition rely in a deep learning-pipeline. Nonetheless, these methods require a large amount of data that is not easy to obtain. In addition to that, the majority of them exploit features of the datasets, like the fact of being CAD models to create rendered representation which will not work in real life because the 3D sensors provide point clouds. We propose a novel global descriptor for point clouds which takes advantage of the fractal dimension of the objects. Our approach introduces many benefits, such as being agnostic to the density of points of the sample, number of points in the input cloud, sensor of choice, and noise up to a level, and it works on real life point cloud data provided by commercial sensors. We tested our descriptor for 3D object recognition using ModelNet, which is a well-known dataset for that task. Our approach achieves 92.84% accuracy on the ModelNet10, and 88.74% accuracy on the ModelNet40.

show abstract

“…This engine employs 2D CNN to extract view features and matches them to calculate the similarity between 3D models. Seout et al [41] propose a stereographic projection neural network (SPNet). This method learns the feature representation of a 3D model by transforming the input 3D model into a 2D planar image using stereo projection.…”

Section: Related Workmentioning

confidence: 99%

Semantic and Context Information Fusion Network for View-Based 3D Model Classification and Retrieval

et al. 2020

View full text Add to dashboard Cite

In recent years, with the rapid development of 3D technology, view-based methods have shown excellent performance in both 3D model classification and retrieval tasks. In view-based methods, how to aggregate multi-view features is a key issue. There are two commonly used solutions in the existing methods: 1) Use pooling strategy to merge multi-view features, but it ignores the context information contained in the continuous view sequence. 2) Leverage grouping strategy or long short term memory networks (LSTM) to select representative views of the 3D model, however, it easily neglects the semantic information of individual views. In this paper, we propose a novel Semantic and Context information Fusion Network (SCFN) to compensate for these drawbacks. First, we render views from multiple perspectives of the 3D model and extract the raw feature of the individual view by 2D convolutional neural networks (CNN). Then we design the channel attention mechanism (CAM) to exploit the view-wise semantic information. By modeling the correlation among view feature channels, we can assign higher weights to useful feature attributes, while suppressing the useless. Next, we propose a context information fusion module (CFM) to fuse multiple view features to obtain a compact 3D representation. Extensive experiments are conducted on three popular datasets, i.e., ModelNet10, ModelNet40, and ShapeNetCore55, which can demonstrate the superiority of the proposed method comparing to the state-of-the-arts on both 3D classification and retrieval tasks.

show abstract

SPNet: Deep 3D Object Classification and Retrieval Using Stereographic Projection

Cited by 43 publications

References 28 publications

Point Cloud Semantic Segmentation Using a Deep Learning Framework for Cultural Heritage

Point Cloud Semantic Segmentation Using a Deep Learning Framework for Cultural Heritage

A Voxelized Fractal Descriptor for 3D Object Recognition

Semantic and Context Information Fusion Network for View-Based 3D Model Classification and Retrieval

Contact Info

Product

Resources

About