HyperPocket: Generative Point Cloud Completion

Spurek, Przemysław; Kasymov, Artur; Mazur, Marcin; Janik, Diana; Tadeja, Sławomir K.; Struski, Łukasz; Tabor, Jacek; Trzciński, Tomasz Piotr

doi:10.48550/arxiv.2102.05973

Cited by 5 publications

(5 citation statements)

References 26 publications

(46 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, they also designed a refinement component to evenly distribute the reconstructed coordinates, while also reducing noise and outliers. Surek et al [54] redefined the point cloud completion problem as an object hallucination task. They proposed the Hyperpocket architecture, which used an auto-encoder based on a hypernetwork paradigm design.…”

Section: B Learning-based Methodsmentioning

confidence: 99%

A Survey of Point Cloud Completion

Zhuang,

Zhi,

Han

et al. 2024

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Point cloud completion is able to estimate the complete point cloud starting from the missing point cloud, which obtains higher quality point cloud data for widely used in remote sensing 3D modeling, medical imaging, robot vision, etc. The challenge of point clouds mainly lies in the disordered and unstructured nature, which makes point cloud completion difficult. Point cloud completion research can be broadly categorized into traditional approaches and deep learning based methods. Recently, intensive research has primarily focused on deep learning based methods, given robustness and efficiency in processing the substantial missing data encountered in complex real world scenes. In addition, deep learning based methods have higher generalization performance. To stimulate future research, this survey presents a comprehensive review of existing traditional and deep learning based 3D point cloud completion methods. This review conducts extensive examinations of each stage of the process, providing a compilation of famous datasets, metrics, and their respective characteristics. Additionally, the impacts of subsequent downstream application tasks with or without completion are discussed, followed by some potential future issues in point cloud completion.

show abstract

Section: B Learning-based Methodsmentioning

confidence: 99%

A Survey of Point Cloud Completion

Zhuang,

Zhi,

Han

et al. 2024

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

show abstract

“…There are no paired completion instances in the training dataset. Spurek et al [105] introduced a Variational Autoencoder architecture named HyperPocket, which is capable of disentangling latent representations and thus generating multiple variants of completed 3D point clouds (Fig. 16).…”

Section: F Variational Autoencoders (Vaes)-based Methodsmentioning

confidence: 99%

Comprehensive Review of Deep Learning-Based 3D Point Cloud Completion Processing and Analysis

Fei¹,

Yang²,

Chen³

et al. 2022

Preprint

View full text Add to dashboard Cite

Point cloud completion is a generation and estimation issue derived from the partial point clouds, which plays a vital role in the applications in 3D computer vision. The progress of deep learning (DL) has impressively improved the capability and robustness of point cloud completion. However, the quality of completed point clouds is still needed to be further enhanced to meet the practical utilization. Therefore, this work aims to conduct a comprehensive survey on various methods, including point-based, convolution-based, graph-based, and generative model-based approaches, etc. And this survey summarizes the comparisons among these methods to provoke further research insights. Besides, this review sums up the commonly used datasets and illustrates the applications of point cloud completion. Eventually, we also discussed possible research trends in this promptly expanding field.

show abstract

“…Huang et al [14] propose an efficient and fast-converging recurrent forward network that decreases the memory cost by sharing parameters. HyperPocket [36] first completes the point clouds with an autoencoder-based architecture and then leverages a hypernetwork to make point clouds adapted to the scenes which fill the holes in the scenes.…”

Section: Related Workmentioning

confidence: 99%

Completing Partial Point Clouds with Outliers by Collaborative Completion and Segmentation

Ma¹,

Yang²,

Guo³

et al. 2022

Preprint

View full text Add to dashboard Cite

Most existing point cloud completion methods are only applicable to partial point clouds without any noises and outliers, which does not always hold in practice. We propose in this paper an end-toend network, named CS-Net, to complete the point clouds contaminated by noises or containing outliers. In our CS-Net, the completion and segmentation modules work collaboratively to promote each other, benefited from our specifically designed cascaded structure. With the help of segmentation, more clean point cloud is fed into the completion module. We design a novel completion decoder which harnesses the labels obtained by segmentation together with FPS to purify the point cloud and leverages KNN-grouping for better generation. The completion and segmentation modules work alternately share the useful information from each other to gradually improve the quality of prediction. To train our network, we build a dataset to simulate the real case where incomplete point clouds contain outliers. Our comprehensive experiments and comparisons against state-of-the-art completion methods demonstrate our superiority. We also compare with the scheme of segmentation followed by completion and their end-to-end fusion, which also proves our efficacy.

show abstract

HyperPocket: Generative Point Cloud Completion

Cited by 5 publications

References 26 publications

A Survey of Point Cloud Completion

A Survey of Point Cloud Completion

Comprehensive Review of Deep Learning-Based 3D Point Cloud Completion Processing and Analysis

Completing Partial Point Clouds with Outliers by Collaborative Completion and Segmentation

Contact Info

Product

Resources

About