PointGrow: Autoregressively Learned Point Cloud Generation with Self-Attention

@article{Sun2020PointGrowAL,
  title={PointGrow: Autoregressively Learned Point Cloud Generation with Self-Attention},
  author={Yongbin Sun and Yue Wang and Ziwei Liu and Joshua E. Siegel and Sanjay E. Sarma},
  journal={2020 IEEE Winter Conference on Applications of Computer Vision (WACV)},
  year={2020},
  pages={61-70}
}
  • Yongbin Sun, Yue Wang, +2 authors S. Sarma
  • Published 12 October 2018
  • Computer Science
  • 2020 IEEE Winter Conference on Applications of Computer Vision (WACV)
Generating 3D point clouds is challenging yet highly desired. This work presents a novel autoregressive model, PointGrow, which can generate diverse and realistic point cloud samples from scratch or conditioned on semantic contexts. This model operates recurrently, with each point sampled according to a conditional distribution given its previously-generated points, allowing inter-point correlations to be well-exploited and 3D shape generative processes to be better interpreted. Since point… Expand
PointFlow: 3D Point Cloud Generation With Continuous Normalizing Flows
TLDR
A principled probabilistic framework to generate 3D point clouds by modeling them as a distribution of distributions with the invertibility of normalizing flows enables the computation of the likelihood during training and allows the model to train in the variational inference framework. Expand
Geometric Feedback Network for Point Cloud Classification
TLDR
A network designed as a feedback mechanism, a procedure allowing the modification of the output via as a response to the output, to comprehensively capture the local features of 3D point clouds is proposed. Expand
Progressive Seed Generation Auto-encoder for Unsupervised Point Cloud Learning
With the development of 3D scanning technologies, 3D vision tasks have become a popular research area. Owing to the large amount of data acquired by sensors, unsupervised learning is essential forExpand
Learning Gradient Fields for Shape Generation
TLDR
This work generates point clouds by performing stochastic gradient ascent on an unnormalized probability density, thereby moving sampled points toward the high-likelihood regions and allowing for extraction of a high-quality implicit surface. Expand
SAPCGAN: Self-Attention based Generative Adversarial Network for Point Clouds
  • Yushi Li, G. Baciu
  • Computer Science
  • 2020 IEEE 19th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC)
  • 2020
TLDR
This paper designs a novel Generative Adversarial Network (GAN) architecture to generate point clouds resembling the ground truth that could be used for unsupervised learning of 3D shapes, and proposes a cognitive self-attention based learning approach to aggregate global representation of3D shapes from point cloud data. Expand
A Progressive Conditional Generative Adversarial Network for Generating Dense and Colored 3D Point Clouds
TLDR
A novel conditional generative adversarial network that creates dense 3D point clouds, with color, for assorted classes of objects in an unsupervised manner is introduced and a point transformer that progressively grows the network through the use of graph convolutions is proposed. Expand
Tranquil Clouds: Neural Networks for Learning Temporally Coherent Features in Point Clouds
TLDR
A novel temporal loss function is proposed that takes into account higher time derivatives of the point positions, and encourages mingling, i.e., to prevent the aforementioned halos and is combined in a super-resolution method with a truncation approach to flexibly adapt the size of the generated positions. Expand
Progressive Point Cloud Deconvolution Generation Network
TLDR
An effective point cloud generation method that can generate multi-resolution point clouds of the same shape from a latent vector is proposed and a shape-preserving adversarial loss is proposed to train the point cloud deconvolution generation network. Expand
Learning to Sample
TLDR
It is shown that it is better to learn how to sample, and proposes a deep network to simplify 3D point clouds, termed S-NET, which takes a point cloud and produces a smaller point cloud that is optimized for a particular task. Expand
HSGAN: Hierarchical Graph Learning for Point Cloud Generation
  • Yushi Li, G. Baciu
  • Computer Science, Medicine
  • IEEE Transactions on Image Processing
  • 2021
TLDR
This work proposes a novel Generative Adversarial Network (GAN), named HSGAN, or Hierarchical Self-Attention GAN, with remarkable properties for 3D shape generation, and presents a new adversarial loss to maintain the training stability and overcome the potential mode collapse of traditional GANs. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 85 REFERENCES
Multiresolution Tree Networks for 3D Point Cloud Processing
TLDR
This model represents a 3D shape as a set of locality-preserving 1D ordered list of points at multiple resolutions, which allows efficient feed-forward processing through 1D convolutions, coarse-to-fine analysis through a multi-grid architecture, and it leads to faster convergence and small memory footprint during training. Expand
Attentional ShapeContextNet for Point Cloud Recognition
TLDR
The resulting model, called ShapeContextNet, consists of a hierarchy with modules not relying on a fixed grid while still enjoying properties similar to those in convolutional neural networks - being able to capture and propagate the object part information. Expand
PU-Net: Point Cloud Upsampling Network
TLDR
A data-driven point cloud upsampling technique to learn multi-level features per point and expand the point set via a multi-branch convolution unit implicitly in feature space, which shows that its upsampled points have better uniformity and are located closer to the underlying surfaces. Expand
Representation Learning and Adversarial Generation of 3D Point Clouds
TLDR
This paper introduces a deep autoencoder network for point clouds, which outperforms the state of the art in 3D recognition tasks, and designs GAN architectures to generate novel point-clouds. Expand
PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
TLDR
This paper designs a novel type of neural network that directly consumes point clouds, which well respects the permutation invariance of points in the input and provides a unified architecture for applications ranging from object classification, part segmentation, to scene semantic parsing. Expand
Escape from Cells: Deep Kd-Networks for the Recognition of 3D Point Cloud Models
TLDR
A new deep learning architecture that is designed for 3D model recognition tasks and works with unstructured point clouds, Kd-networks, which demonstrates competitive performance in a number of shape recognition tasks such as shape classification, shape retrieval and shape part segmentation. Expand
FoldingNet: Point Cloud Auto-Encoder via Deep Grid Deformation
TLDR
A novel end-to-end deep auto-encoder is proposed to address unsupervised learning challenges on point clouds, and is shown, in theory, to be a generic architecture that is able to reconstruct an arbitrary point cloud from a 2D grid. Expand
RGCNN: Regularized Graph CNN for Point Cloud Segmentation
TLDR
A regularized graph convolutional neural network (RGCNN) that directly consumes point clouds is proposed that significantly reduces the computational complexity while achieving competitive performance with the state of the art. Expand
Learning Efficient Point Cloud Generation for Dense 3D Object Reconstruction
TLDR
This paper uses 2D convolutional operations to predict the 3D structure from multiple viewpoints and jointly apply geometric reasoning with 2D projection optimization, and introduces the pseudo-renderer, a differentiable module to approximate the true rendering operation, to synthesize novel depth maps for optimization. Expand
Deep Learning on Point Sets for 3 D Classification and Segmentation
Point cloud is an important type of geometric data structure. Due to its irregular format, most researchers transform such data to regular 3D voxel grids or collections of images. This, however,Expand
...
1
2
3
4
5
...