HyperPocket: Generative Point Cloud Completion

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

doi:10.1109/iros47612.2022.9981829

Cited by 8 publications

(8 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This means, despite the progress made to generalise completion algorithms to different type of inputs, there are still limitations that arise from the training datasets. We discuss more details in Section V. Multiple point clouds from the same object: Spurek et al [34] take two partial inputs, transform them to feature vectors separately and use complimentary information from their encodings to produce a complete 3D shape. To the best of our knowledge, [34] is the only work that uniquely uses multiple point clouds for feature extraction without registration.…”

Section: A Inputsmentioning

confidence: 99%

“…The completion is conditioned on a learned multimodal distribution of possible results. This approach was also followed by [34], [62], [63]. In addition, Cui et al [63] produce a completed point cloud per object with uncertainty maps.…”

Section: B Outputsmentioning

confidence: 99%

“…One path reconstructs complete point clouds from a complete input, and the other generates complete point cloud from a partial input. Hyperpocket [34] splits the point cloud processing into two disjoint data streams of partial input and "pockets": empty spaces left by the missing part of the objects. Li et al [117] propose to decode a lowresolution point cloud first and perform path-wise noise-aware up-sampling and recover the details patch by patch.…”

Section: E Effective Feature Representationmentioning

confidence: 99%

“…Apart from GANs, new generative models (e.g., denoising diffusion [53], [133], [143]- [146], probabilistic VAEs [34], [107]) are showing promising results in other domains. They may inspire new point cloud completion research.…”

Section: Future Workmentioning

confidence: 99%

See 3 more Smart Citations

Point Cloud Completion: A Survey

Tesema,

Hill,

Jones

et al. 2024

IEEE Trans. Visual. Comput. Graphics

View full text Add to dashboard Cite

Point cloud completion is the task of producing a complete 3D shape given an input of a partial point cloud. It has become a vital process in 3D computer graphics, vision and applications such as autonomous driving, robotics, and augmented reality. These applications often rely on the presence of a complete 3D representation of the environment. Over the past few years, many completion algorithms have been proposed and a substantial amount of research has been carried out. However, there are not many in-depth surveys that summarise the research progress in such a way that allows users to make an informed choice of what algorithms to employ given the type of data they have, the end result they want, the challenges they may face and the possible strategies they could use. In this study, we present a comprehensive survey and classification of papers on point cloud completion untill August 2023 based on the strategies, techniques, inputs, outputs, and network architectures. We will also cover datasets, evaluation methods, and application areas in point cloud completion. Finally, we discuss challenges faced by the research community and future research directions.

show abstract

Section: A Inputsmentioning

confidence: 99%

Section: B Outputsmentioning

confidence: 99%

Section: E Effective Feature Representationmentioning

confidence: 99%

Section: Future Workmentioning

confidence: 99%

See 2 more Smart Citations

Point Cloud Completion: A Survey

Tesema,

Hill,

Jones

et al. 2024

IEEE Trans. Visual. Comput. Graphics

View full text Add to dashboard Cite

show abstract

“…The primary network's weights can be adjusted based on specific inputs, resulting in a more expressive and adaptive model. Hypernetworks have been used in various applications such as learning implicit neural representations [9], semantic segmentation [23], 3D scene representation and modeling [19,33,34] and continuous learning [39], to name a few.…”

Section: Hypernetworkmentioning

confidence: 99%

HyperPose: Camera Pose Localization using Attention Hypernetworks

Ferens¹,

Keller²

2023

Preprint

View full text Add to dashboard Cite

In this study, we propose the use of attention hypernetworks in camera pose localization. The dynamic nature of natural scenes, including changes in environment, perspective, and lighting, creates an inherent domain gap between the training and test sets that limits the accuracy of contemporary localization networks. To overcome this issue, we suggest a camera pose regressor that integrates a hypernetwork. During inference, the hypernetwork generates adaptive weights for the localization regression heads based on the input image, effectively reducing the domain gap. We also suggest the use of a Transformer-Encoder as the hypernetwork, instead of the common multilayer perceptron, to derive an attention hypernetwork. The proposed approach achieves superior results compared to state-of-the-art methods on contemporary datasets. To the best of our knowledge, this is the first instance of using hypernetworks in camera pose regression, as well as using Transformer-Encoders as hypernetworks. We make our code publicly available 1 .

show abstract