Spectral-GANs for High-Resolution 3D Point-cloud Generation

Ramasinghe, Sameera; Khan, Salman; Barnes, Nick; Gould, Stephen J.

doi:10.1109/iros45743.2020.9341265

Cited by 28 publications

(26 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Achlioptas et al [2018] introduce the first set of deep generative models to produce point clouds from a Gaussian noise vector, including an r-GAN that operates on a raw point cloud input and an l-GAN that operates on the bottleneck latent variables of a pretrained autoencoder. To overcome the redundancy and structural irregularity of point samples, Ramasinghe et al [2019] propose Spectral-GANs to synthesize shapes using a spherical-harmonicsbased representation. Shu et al [2019] propose tree-GAN to perform graph convolutions in a tree and recently extend it into a multi-rooted version.…”

Section: Related Workmentioning

confidence: 99%

Sp-Gan

Hui

2021

ACM Trans. Graph.

View full text Add to dashboard Cite

We present SP-GAN, a new unsupervised sphere-guided generative model for direct synthesis of 3D shapes in the form of point clouds. Compared with existing models, SP-GAN is able to synthesize diverse and high-quality shapes with fine details and promote controllability for part-aware shape generation and manipulation, yet trainable without any parts annotations. In SP-GAN, we incorporate a global prior (uniform points on a sphere) to spatially guide the generative process and attach a local prior (a random latent code) to each sphere point to provide local details. The key insight in our design is to disentangle the complex 3D shape generation task into a global shape modeling and a local structure adjustment, to ease the learning process and enhance the shape generation quality. Also, our model forms an implicit dense correspondence between the sphere points and points in every generated shape, enabling various forms of structure-aware shape manipulations such as part editing, part-wise shape interpolation, and multi-shape part composition, etc., beyond the existing generative models. Experimental results, which include both visual and quantitative evaluations, demonstrate that our model is able to synthesize diverse point clouds with fine details and less noise, as compared with the state-of-the-art models.

show abstract

Section: Related Workmentioning

confidence: 99%

Sp-Gan

Hui

2021

ACM Trans. Graph.

View full text Add to dashboard Cite

show abstract

“…PC-GAN employs a permutation-invariant generator [26]. Spectral-GAN handles point clouds in the spectral domain [36].…”

Section: Related Workmentioning

confidence: 99%

“…The other GAN-based methods [36,39,43] used different experimental settings. Under the same experimental settings, we confirmed that ChartPointFlow outperformed these methods (see Appendix C.4).…”

Section: Generation Taskmentioning

confidence: 99%

“…Point clouds can capture a much higher resolution than voxels, and can be processed using simpler manipulations than meshes. By leveraging the flexibility of deep learning, a deep generative model of point clouds enables a variety of synthesis tasks such as generation, reconstruction, and super-resolution [1,2,13,18,26,36,39,43,47]. Because it is difficult to measure the quality of a generated point cloud numerically, most studies employ flow-based generative models [6,10,20] or generative adversarial networks (GANs) [9].…”

mentioning

confidence: 99%

“…We used pretrained models of PointFlow 2 and SoftFlow 3 distributed by the original authors. ChartPointFlow generated samples more similar than others, suggesting that it generated a variety of shapes.The other GAN-based methods[36,39,43] used different experimental settings. Under the same experimental settings, we confirmed that ChartPointFlow outperformed these methods (see Appendix C.4).…”

mentioning

confidence: 99%

See 2 more Smart Citations

ChartPointFlow for Topology-Aware 3D Point Cloud Generation

Kimura

Matsubara

Uehara

2021

Proceedings of the 29th ACM International Conference on Multimedia

View full text Add to dashboard Cite

A point cloud serves as a representation of the surface of a threedimensional (3D) shape. Deep generative models have been adapted to model their variations typically using a map from a ball-like set of latent variables. However, previous approaches did not pay much attention to the topological structure of a point cloud, despite that a continuous map cannot express the varying numbers of holes and intersections. Moreover, a point cloud is often composed of multiple subparts, and it is also difficult to express. In this study, we propose ChartPointFlow, a flow-based generative model with multiple latent labels for 3D point clouds. Each label is assigned to points in an unsupervised manner. Then, a map conditioned on a label is assigned to a continuous subset of a point cloud, similar to a chart of a manifold. This enables our proposed model to preserve the topological structure with clear boundaries, whereas previous approaches tend to generate blurry point clouds and fail to generate holes. The experimental results demonstrate that ChartPointFlow achieves state-of-the-art performance in terms of generation and reconstruction compared with other point cloud generators. Moreover, ChartPointFlow divides an object into semantic subparts using charts, and it demonstrates superior performance in case of unsupervised segmentation. CCS CONCEPTS• Computing methodologies → Point-based models.

show abstract

Point cloud synthesis with stochastic differential equations

Wang

Liu

et al. 2023

Computer Animation & Virtual

View full text Add to dashboard Cite

In this article, we propose a point cloud synthesis method based on stochastic differential equations. We view the point cloud generation process as smoothly transforming from a known prior distribution toward the high‐likelihood shape by point‐level denoising. We introduce a conditional corrector sampler to improve the quality of point clouds. By leveraging Markov chain Monte Carlo sample, our method can synthesize realistic point clouds. We additionally prove that our approach can be trained in an auto‐encoding fashion and reconstruct the point cloud faithfully. Furthermore, our model can be extended on a downstream application of point cloud completion. Experimental results demonstrate the effectiveness and efficiency of our method.

show abstract

Spectral-GANs for High-Resolution 3D Point-cloud Generation

Cited by 28 publications

References 20 publications

Sp-Gan

Sp-Gan

ChartPointFlow for Topology-Aware 3D Point Cloud Generation

Point cloud synthesis with stochastic differential equations

Contact Info

Product

Resources

About