3D deep shape descriptor

By Yi Fang, J. Xie, Guoxian Dai, M. Wang, Fan Zhu, Tiantian Xu, Edward K. Wong. 2015

209 citations recorded by the source corpus.

Subfields: Computational Mechanics, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Mechanics

In Computer Vision and Pattern Recognition

Citations in the corpus

PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation (2016, methodology): “Feature-based DNNs: [6, 8] firstly convert the 3D data into a vector, by extracting traditional shape features and then use a fully connected net to classify the shape.”
Deep Sliding Shapes for Amodal 3D Object Detection in RGB-D Images (2015, methodology): “Furthermore, compared to methods using hand-crafted 3D features [5, 31], we desire a representation that encodes the 3D geometry as raw as possible, and let ConvNets learn the most discriminative features from the raw data.”
Distilling Knowledge From Graph Convolutional Networks (2020, methodology): “Deep learning based methods [39, 11, 7, 20, 29, 26] outperform the previous methods that based on hand-crafted feature extractors [1, 3].”
3DMatch: Learning the Matching of Local 3D Geometry in Range Scans (2016, background): “Additionally, several recent works [21, 11] also extract deep learning features from 3D data for the task of object retrieval and classification for CAD models.”
RotationNet: Joint Object Categorization and Pose Estimation Using Multiviews from Unsupervised Viewpoints (2016, methodology): “recently been drawing a lot of attention. Wu et al. [2] introduced a convolutional deep belief network that learns 3D voxel data converted from the CAD models of objects in 40 categories. Fang et al. [3] proposed a method that learns deep neural networks using a heat kernel signature (HKS) [4] as in”
GIFT: A Real-Time and Scalable 3D Shape Search Engine (2016, background): “fﬁciency issue has been more or less ignored by previous works, though enormous efforts have been devoted to retrieval effectiveness, that is to say, to design informative and discriminative features [12, 2, 17, 6, 41, 15, 18] to boost the retrieval accuracy. As suggested in [14], plenty of these al”
Deep Learning on Point Sets for 3 D Classification and Segmentation (2016, methodology): “Feature-based DNNs: [6, 8] firstly convert the 3D data into a vector, by extracting traditional shape features and then use a fully connected net to classify the shape.”
Learning Semantic Deformation Flows with 3D Convolutional Networks (2016, background): “3D feature extraction using fully connected autoencoders [10, 41] and multi-view based CNNs [38] are also actively studied for classification and retrieval.”
Deep Learning Advances in Computer Vision with 3D Data (2017, methodology): “A similar framework was presented in Fang et al. [2015].”
Learning Weight Uncertainty with Stochastic Gradient MCMC for Shape Classification (2016, background): “A discriminative non-linear mapping is learned in [21] to embed traditional shape features.”
Deep Learning 3D Shape Surfaces Using Geometry Images (2016, methodology): “Hence, CNN-based deformable shape analysis methods propose the use of geodesic convolutional filters as patches or model spectral-CNN’s using the eigen decomposition of the Laplace-Beltrami operator to derive robust shape descriptors [1,6,19].”
3DMatch: Learning Local Geometric Descriptors from RGB-D Reconstructions (2016, background): “3D ShapeNets [39] introduced 3D deep learning for modeling 3D shapes, and several recent works [23, 11, 34] also compute deep features from 3D data for the task of object retrieval and classification.”