Deep Learning for 3D Shape Classification based on Volumetric Density and Surface Approximation Clues

Minto, Ludovico; Zanuttigh, Pietro; Pagnutti, Giampaolo

doi:10.5220/0006619103170324

Cited by 16 publications

(11 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…No code was available at the time of writing. The classification approach described by Minto et al [46] uses axis-aligned images with multiple rendered modalities: depth, voxel density (X-ray-like image), and estimated surface curvature constructed by fitting a parametric surface (NURBS) to the points constructed from depth-image samples. The images are passed to a 4-or 5-layer CNN, whose weights are shared among branches processing the images of the same modality, which are rendered from viewpoints rotated around the vertical axis.…”

Section: Multiple Modalitiesmentioning

confidence: 99%

Survey and Evaluation of Neural 3D Shape Classification Approaches

Mirbauer¹,

Krabec²,

Křivánek³

et al. 2021

Preprint

View full text Add to dashboard Cite

<div> <div> <div> <p>Classification of 3D objects – the selection of a category in which each object belongs – is of great interest in the field of machine learning. Numerous researchers use deep neural networks to address this problem, altering the network architecture and representation of the 3D shape used as an input. To investigate the effectiveness of their approaches, we conduct an extensive survey of existing methods and identify common ideas by which we categorize them into a taxonomy. Second, we evaluate 11 selected classification networks on three 3D object datasets, extending the evaluation to a larger dataset on which most of the selected approaches have not been tested yet. For this, we provide a framework for converting shapes from common 3D mesh formats into formats native to each network, and for training and evaluating different classification approaches on this data. Despite being generally unable to reach the accuracies reported in the original papers, we can compare the relative performance of the approaches as well as their performance when changing datasets as the only variable to provide valuable insights into performance on different kinds of data. We make our code available to simplify running training experiments with multiple neural networks with different prerequisites. </p> </div> </div> </div>

show abstract

Section: Multiple Modalitiesmentioning

confidence: 99%

Survey and Evaluation of Neural 3D Shape Classification Approaches

Mirbauer¹,

Krabec²,

Křivánek³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Other works are also based on this latter approach [18]. In addition to this, some works mix several object representations in order to improve the learning, including voxelizations [19].…”

Section: Related Workmentioning

confidence: 99%

A GPU-Based Framework for Generating Implicit Datasets of Voxelized Polygonal Models for the Training of 3D Convolutional Neural Networks

et al. 2020

View full text Add to dashboard Cite

In this paper we present an efficient GPU-based framework to dynamically perform the voxelization of polygonal models for training 3D convolutional neural networks. It is designed to manage the dataset augmentation by using efficient geometric transformations and random vertex displacements in GPU. With the proposed system, every voxelization is carried out on-the-fly for directly feeding the network. The computing performance with this approach is much better than with the standard method, that carries out every voxelization of each model separately and has much higher data processing overhead. The core voxelization algorithm works by using the standard rendering pipeline of the GPU. It generates binary voxels for both the interior and the surface of the models. Moreover, it is simple, concise and very compatible with commodity hardware, as it neither uses complex data structures nor needs vendor-specific hardware or additional dependencies. This framework dramatically reduces the input/output operations, and completely eliminates the storage footprint of the voxelization dataset, managing it as an implicit dataset.

show abstract

“…In fact, most computations are not required due to the sparsity of 3D data. To deal with the sparsity problem, literatures [14]- [16] directly exploit the sparsity, and literature [17] takes surface approximation clue into account. But they are too complex to be used in large or flexible networks.…”

Section: Related Workmentioning

confidence: 99%

Using Deep Learning in Semantic Classification for Point Cloud Data

Yao¹,

Guo

et al. 2019

IEEE Access

View full text Add to dashboard Cite

Point cloud is an important 3D data structure, but its irregular format brings great challenges to deep learning. The advent of PointNet makes it possible to process irregular point cloud data by neural networks directly. As an extension of PointNet, PointNet++ can extract local features, which makes it perform better than PointNet in processing point cloud data. But in practice, it is common that the density of a point set usually varies with the location, which makes the computation overhead of PointNet++ very heavy. To deal with it, we propose an octree grouping-based network structure for PointNet++, named Octree-Grouping-PointNet++ (OG-PointNet++). It determines the point density by constructing an unbalanced octree for the point cloud, and groups point according to the point density. These point groups are assigned to different layers according to their density, and the local feature of each group is extracted by PointNet++. The global feature is obtained from the last abstract layer and used for classification and segmentation. The experiments show its competitive performance in many 3D tasks, such as object classification and semantic segmentation.

show abstract

Deep Learning for 3D Shape Classification based on Volumetric Density and Surface Approximation Clues

Cited by 16 publications

References 0 publications

Survey and Evaluation of Neural 3D Shape Classification Approaches

Survey and Evaluation of Neural 3D Shape Classification Approaches

A GPU-Based Framework for Generating Implicit Datasets of Voxelized Polygonal Models for the Training of 3D Convolutional Neural Networks

Using Deep Learning in Semantic Classification for Point Cloud Data

Contact Info

Product

Resources

About