MeshNet: Mesh Neural Network for 3D Shape Representation

Yuan, Feng; Feng, Yifan; You, Haoxuan; Zhao, Xibin; Gao, Yue

doi:10.1609/aaai.v33i01.33018279

Cited by 231 publications

(147 citation statements)

References 3 publications

Supporting

Mentioning

146

Contrasting

Order By: Relevance

“…The model-based methods directly process the raw representations of 3D shapes, including voxel [6], [7], [8], polygon mesh or surfaces [9], [10], [11] and point cloud [2], [12], [13]. Concretely, Feng et al [14] proposed a novel Mesh neural network named MeshNet, which introduce a general architecture with available and effective blocks to capture and aggregate features of polygon faces in 3D shapes. Meanwhile, the complexity and irregularity problems of mesh are effectively solved.…”

Section: A Model-based Methodsmentioning

confidence: 99%

MPAN: Multi-Part Attention Network for Point Cloud Based 3D Shape Retrieval

Zhao

et al. 2020

IEEE Access

View full text Add to dashboard Cite

3D shape retrieval is an important researching field due to its wide applications in computer vision and multimedia fields. With the development of deep learning technology, great progress has been made in recent years and lots of methods have achieved promising 3D shape retrieval results. Due to the effective description of point cloud data on structural information for 3D shapes, lots of methods based on point cloud data format are proposed for better shape representation. However, most of them focus on extracting a global descrisptor from the whole 3D shape while the local features and detailed structural information are ignored, which negatively affect the effectiveness of shape descriptors. In addition, these methods also ignore the correlations among different parts of point clouds, which may introduce redundant information to the final shape descriptors. In order to address these issues, we propose a Multipart attention network (MPAN) for 3D model retrieval based on point cloud. Firstly, we segment a 3D shape into multiple parts by employing a pre-trained PointNet++ segmentation model. After extracting the local features from them, we introduce a novel self-attention mechanism to explore the correlations between different parts. Meanwhile, by considering the structural relevance of them, the redundancy for representing 3D shapes is removed while the effective information is utilized. Finally, informative and discriminative shape descriptors, considering both local features and spatial correlations, are generated for 3D shape retrieval task. To validate the effectiveness of our method, we conduct several experiments on the public 3D shape benchmark, ShapeNetPart dataset. Experimental results and comparisons with state-of-the-art methods demonstrate the superiority of our proposed method.

show abstract

Section: A Model-based Methodsmentioning

confidence: 99%

MPAN: Multi-Part Attention Network for Point Cloud Based 3D Shape Retrieval

Zhao

et al. 2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…3D shape retrieval aims to match the relevant 3D shapes, which can be described as 3D mesh [9], voxel grid [8], point cloud [13] or multi-view [1,14], when given a query. The query can be 3D shape or other data representation modalities, such as: text [6], 2D image [3,[15][16][17] and 2D sketch [18], and we unite them as cross-domain 3D shape retrieval.…”

Section: Related Work 21 3d Shape Retrievalmentioning

confidence: 99%

“…Feng et al [20] propose a group-view convolutional neural network (GVCNN) framework to discover the multi-view correlation in a hierarchical strategy, including view-level, grouplevel and shape-level. Compared with discovering the multi-view context for describing 3D shapes, learning 3D shape representations from the geometric structure, contained in voxel grid [8,10], mesh [9,21] and point clouds [7,13,22,23], seems more reasonable. However, the high computational complexity restricts their practicability and flexibility in real scenarios.…”

Section: Related Work 21 3d Shape Retrievalmentioning

confidence: 99%

“…How to annotate the large-scale unlabelled 3D shapes for 2D-to-3D task. The most successful 3D shape retrieval methods [5,[7][8][9] leverage deep learning via a supervised learning approach, discovering the multi-view context [5] or exploring the geometry structure of point clouds [7], mesh [9] and voxel [10]. Those supervised learning driven methods hold the assumption that we can obtain a large number of manually-annotated 3D shapes in practical applications.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Semantic Consistency Guided Instance Feature Alignment for 2D Image-Based 3D Shape Retrieval

Zhou

Nie

Song

et al. 2020

Proceedings of the 28th ACM International Conference on Multimedia

View full text Add to dashboard Cite

2D image-based 3D shape retrieval (2D-to-3D) investigates the problem of matching the relevant 3D shapes from gallery dataset when given a query image. Recently, adversarial training and environmental style transfer learning have been successful applied to this task and achieved state-of-the-art performance. However, there still exist two problems. First, previous works only concentrate on the connection between the label and representation, where the unique visual characteristics of each instance are paid less attention. Second, the confused features or the transformed images can only cheat the discriminator but can not guarantee the semantic consistency. In another words, features of 2D desk may be mapped nearby the features of 3D chair. In this paper, we propose a novel semantic consistency guided instance feature alignment network (SC-IFA) to address these limitations. SC-IFA mainly consists of two parts, instance visual feature extraction and cross-domain instance feature adaptation. For the first module, unlike previous methods, which merely employ 2D CNN to extract the feature, we additionally maximize the mutual information between the input and feature to enhance the capability of feature representation for each instance. For the second module, we first introduce the margin disparity discrepancy model to mix up the cross-domain features in an adversarial training way. Then, we design two feature translators to transform the feature from one domain to another domain, and impose the translation loss and correlation loss on the transformed features to preserve the semantic consistency. Extensive experimental results on two benchmarks, MI3DOR and MI3DOR-2, verify SC-IFA is superior to the state-of-the-art methods.

show abstract

“…To tackle with them, it is often to convert point clouds to other forms such as voxel grids, meshes and multi-view images. Afterwards, they can be processed by Convolutional Neural Network (CNN) methods [5,6,7,8,9]. As compared with methods using raw point clouds as the input, conversion-based methods do have information loss.…”

Section: Introductionmentioning

confidence: 99%

PointHop: An Explainable Machine Learning Method for Point Cloud Classification

Zhang

You

Kadam

et al. 2020

IEEE Trans. Multimedia

Self Cite

113

View full text Add to dashboard Cite

The PointHop method was recently proposed by Zhang et al. for 3D point cloud classification with unsupervised feature extraction. It has an extremely low training complexity while achieving stateof-the-art classification performance. In this work, we improve the PointHop method furthermore in two aspects: 1) reducing its model complexity in terms of the model parameter number and 2) ordering discriminant features automatically based on the cross-entropy criterion. The resulting method is called PointHop++. The first improvement is essential for wearable and mobile computing while the second improvement bridges statistics-based and optimization-based machine learning methodologies. With experiments conducted on the ModelNet40 benchmark dataset, we show that the PointHop++ method performs on par with deep neural network (DNN) solutions and surpasses other unsupervised feature extraction methods.

show abstract

MeshNet: Mesh Neural Network for 3D Shape Representation

Cited by 231 publications

References 3 publications

MPAN: Multi-Part Attention Network for Point Cloud Based 3D Shape Retrieval

MPAN: Multi-Part Attention Network for Point Cloud Based 3D Shape Retrieval

Semantic Consistency Guided Instance Feature Alignment for 2D Image-Based 3D Shape Retrieval

PointHop: An Explainable Machine Learning Method for Point Cloud Classification

Contact Info

Product

Resources

About