3D ShapeNets: A deep representation for volumetric shapes

By Zhirong Wu, Shuran Song, Aditya Khosla, Fisher Yu, Linguang Zhang, Xiaoou Tang, Jianxiong Xiao. 2014

6,540 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computational Mechanics, Computer Vision and Pattern Recognition, Generative Models

How researchers see this paper

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

In Aerospace Engineering

In Computational Mechanics

In Computer Vision and Pattern Recognition

In Generative Models

Citations in the corpus

Weight Standardization (2019, methodology): “Here, we show the generalizability of our method to point cloud classiﬁcation by evaluating our method on Mod-elNet40 [43], which contains 40 categories of CAD models, including 9,843 shapes for training and 2,468 for testing.”
Learning Descriptor Networks for 3D Shape Synthesis and Analysis (2018, methodology): “[23] 88.4% PANORAMA-NN [19] 91.1% ECC [22] 90.0% 3D ShapeNets [29] 83.5% DeepPano [21] 85.5% SPH [10] 79.8% VConv-DAE [20] 80.5% 3D-GAN [28] 91.0% 3D DescriptorNet (ours) 92.4 %”
Perceiver: General Perception with Iterative Attention (2021, methodology): “We train the Perceiver architecture on images from ImageNet (Deng et al., 2009) (left), video and audio from AudioSet (Gemmeke et al., 2017) (considered both multi-and uni-modally) (center), and 3D point clouds from ModelNet40 (Wu et al., 2015) (right).”
Geometric Deep Learning on Graphs and Manifolds Using Mixture Model CNNs (2016, background): “In deformable 3D shape analysis applications, the key advantage of our approach is that it is intrinsic and thus deformation-invariant by construction, as opposed to Euclidean models [36, 43, 41, 29] that in general require significantly higher complexity and huge training sets to learn the deformat”
PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation (2016, methodology): “We evaluate our model on the ModelNet40 [29] shape classification benchmark.”
3D Instance Segmentation of MVS Buildings (2021, methodology): “Volumetric methods ease this issue using a 3D grid representation, which is notoriously expensive in terms of computational efficiency and memory consumption [4], [12], [36], [37], [38], [39].”
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space (2017, methodology): “Datasets We evaluate on four datasets ranging from 2D objects (MNIST [11]), 3D objects (ModelNet40 [31] rigid object, SHREC15 [12] non-rigid object) to real 3D scenes (ScanNet [5]).”
Fast Graph Representation Learning with PyTorch Geometric (2019, methodology): “In addition, we provide embedded datasets like MNIST superpixels (Monti et al., 2017), FAUST (Bogo et al., 2014), ModelNet10/40 (Wu et al., 2015), ShapeNet (Chang et al., 2015), COMA (Ranjan et al., 2018), and the PCPNet dataset from Guerrero et al. (2018).”
Occupancy Networks: Learning 3D Reconstruction in Function Space (2018, background): “Early works have considered the problem of reconstructing 3D geometry from a single image using 3D convolutional neural networks which operate on voxel grids [9, 68, 77].”
SMASH: One-Shot Model Architecture Search through HyperNetworks (2017, methodology): “We validate our one-Shot Model Architecture Search through Hypernetworks (SMASH) for Convolutional Neural Networks (CNN) on CIFAR-10 and CIFAR-100 [19], Imagenet32x32 [7], ModelNet10 [41], and STL-10 [8], achieving competitive performance with similarly-sized hand-designed networks.”
Set Transformer (2018, background): “Other problems such as 3D shape recognition (Wu et al., 2015; Shi et al., 2015; Su et al., 2015; Charles et al., 2017), sequence ordering (Vinyals et al., 2016), and various set operations (Muandet et al., 2012; Oliva et al., 2013; Edwards & Storkey, 2017; Zaheer et al., 2017) can also be viewed as…”
SE(3)-Transformers: 3D Roto-Translation Equivariant Attention Networks (2020, methodology): “Despite the dataset not playing to the strengths of our model (full SE(3)-invariance) and a much lower number of input points, the performance is competitive with models specifically designed for object classification - PointGLR [23], for instance, is pre-trained on the larger ModelNet40 dataset [41”
Tensor Field Networks: Rotation- and Translation-Equivariant Neural Networks for 3D Point Clouds (2018, methodology): “We have successfully trained tensor ﬁeld networks on large standard datasets, including QM9 energy [26], MD17 molecular dynamics forces [27], and ModelNet40 [28] classiﬁcation.”
Transformers in Vision: A Survey (2021, methodology): “The experiments are reported on 3D shape classification, normal estimation and segmentation tasks on ModelNet40 [175] and ShapeNet [176] datasets.”
Geometric Deep Learning: Going beyond Euclidean data (2016, background): “as range images [98], [99] or rasterized volumes [100], [101].”
ScanNet: Richly-Annotated 3D Reconstructions of Indoor Scenes (2017, methodology): “In this section, we summarize the data we collected us-ing our framework to establish the ScanNet dataset.”
OctNet: Learning Deep 3D Representations at High Resolutions (2016, methodology): “In this Section we show the same experiment on ModelNet40 [48].”
Volumetric and Multi-view CNNs for Object Classification on 3D Data (2016, methodology): “Methods in the first group, SPH, LFD, FV, and Su-MVCNN, are trained on a subset of ModelNet40 containing 3,183 training samples.”
ShapeNet: An Information-Rich 3D Model Repository (2015, background): “• Rigid Alignments: Establishing a consistent canonical orientation (e.g., upright and front) for every model is important for various tasks such as visualizing shapes [13], shape classiﬁcation [8] and shape recognition [34].”