On Visual Similarity Based 3D Model Retrieval

By Ding-Yun Chen, Xiao-Pei Tian, E. Shen, M. Ouhyoung. 2003

1,629 citations recorded by the source corpus.

Subfields: Computational Mechanics, Computer Graphics and Computer-Aided Design, 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 Graphics and Computer-Aided Design

In Computer Vision and Pattern Recognition

Citations in the corpus

PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation (2016, background): “Point features often encode certain statistical properties of points and are designed to be invariant to certain transformations, which are typically classified as intrinsic [2, 21, 3] or extrinsic [18, 17, 13, 10, 5].”
Volumetric and Multi-view CNNs for Object Classification on 3D Data (2016, background): “Methods in the first group, SPH, LFD, FV, and Su-MVCNN, are trained on a subset of ModelNet40 containing 3,183 training samples.”
Multi-view Convolutional Neural Networks for 3D Shape Recognition (2015, background): “[5], and Fisher vectors extracted on the same rendered views of the shapes used as input to our networks.”
Learning Implicit Fields for Generative Shape Modeling (2018, methodology): “A less frequently used visual similarity metric in the computer vision community, the light field descriptor (LFD) [8], has been widely adopted in computer graphics.”
Multi-View Silhouette and Depth Decomposition for High Resolution 3D Object Representation (2018, neutral): “Multi-View Representation Our work connects to multi-view representations which capture the characteristics of a 3D object from multiple viewpoints in 2D [17, 26, 42, 32, 12, 39, 34], such as decomposing image silhouettes [23? ], Light Field Descriptors [2], and 2D panoramic mapping [38].”
Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling (2016, neutral): “…VoxNet [Maturana and Scherer, 2015] 83.0% 92.0% ORION [Sedaghat et al., 2016] - 93.8 % Unsupervised - SPH [Kazhdan et al., 2003] 68.2% 79.8% LFD [Chen et al., 2003] 75.5% 79.9% T-L Network [Girdhar et al., 2016] 74.4% - VConv-DAE [Sharma et al., 2016] 75.5% 80.5% 3D-GAN (ours) 83.3 % 91.0 %…”
VConv-DAE: Deep Volumetric Shape Learning Without Object Labels (2016, methodology): “For comparison, we also report performance for Light Field descriptor (LFD [20], 4,700 dimensions) and Spherical Harmonic descriptor (SPH [21], 544 dimensions).”
FPNN: Field Probing Neural Networks for 3D Data (2016, background): “3D shapes can be converted into 2D images and represented by descriptors of the converted images [13, 4].”
FusionNet: 3D Object Classification Using Multiple Data Representations (2016, neutral): “Other shape descriptors include the Light Field Descriptor [3], Heat kernel signatures [2] [12] and SPH [11].”
Data-driven grasping with partial sensor data (2009, background): “Although a large number of shape matching algorithms have been presented based on 3D features [25], [17], [28], in recent years the most successful attempts have been based on 2D silhouette images rendered from viewpoints sampled on a sphere and looking in the direction of the model’s center of mass”
What Do Single-View 3D Reconstruction Networks Learn? (2019, neutral): “2, 3 [2] Ding-Yun Chen, Xiao-Pei Tian, Yu-Te Shen, and Ming Ouhyoung.”
Pixels, Voxels, and Views: A Study of Shape Representations for Single View 3D Object Shape Prediction (2018, methodology): “[2] proposes a 3D shape descriptor based on the silhouettes rendered from the 20 vertices of a dodecahedron surrounding the object.”
Deformation-driven shape correspondence via shape recognition (2017, methodology): “To tackle this challenge, we employ a projective approach, which has been shown to be an e ective way to compare 3D shapes [Chen et al. 2003; Qi et al. 2016].”
Deepshape: Deep learned shape descriptor for 3D shape matching and retrieval (2015, background): “In the past decades, plenty of shape descriptors have been proposed, such as theD2 shape distribution [12], statistical moments of the model [31, 24], Fourier descriptor [8] and Eigenvalue Descriptor (EVD)[15].”
Attentional ShapeContextNet for Point Cloud Recognition (2018, background): “In areas outside of computer vision, the 3D shape classification and recognition problem has been extensively studied in computer graphics [7, 12, 28] and robotics [27, 36].”
Learning a Hierarchical Latent-Variable Model of 3D Shapes (2017, neutral): “2% LFD [4] 79.”
A large-scale Shape Benchmark for 3D object retrieval: Toyohashi shape benchmark (2012, methodology): “The Toyohashi Shape Benchmark (TSB) proposed in this paper is a newly constructed benchmark, having 10,000 fully meaningful 3D objects with 352 classes.”