Adaptive Nonrigid Inpainting of Three-Dimensional Point Cloud Geometry

Dinesh, Chinthaka; Bajić, Ivan V.; Cheung, Gene

doi:10.1109/lsp.2018.2831621

Cited by 16 publications

(2 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…KITTI [126] is a real-world dataset featuring 3D scenes related to autonomous driving. Real 3D point-cloud scans are often subject to occlusion and may contain noise, which may necessitate "hole filling" [127] and/or denoising [128] before further use. Among the datasets discussed above, ModelNet10 [119], ModelNet40 [119], ShapeNet [120] and ScanObjectNN [121] have been very popular in the literature on point cloud adversarial attacks and defenses.…”

Section: Datasets and Victim Modelsmentioning

confidence: 99%

Adversarial Attacks and Defenses on 3D Point Cloud Classification: A Survey

Naderi,

Bajić

2023

IEEE Access

Self Cite

View full text Add to dashboard Cite

Deep learning has successfully solved a wide range of tasks in 2D vision as a dominant AI technique. Recently, deep learning on 3D point clouds has become increasingly popular for addressing various tasks in this field. Despite remarkable achievements, deep learning algorithms are vulnerable to adversarial attacks. These attacks are imperceptible to the human eye, but can easily fool deep neural networks in the testing and deployment stage. To encourage future research, this survey summarizes the current progress on adversarial attack and defense techniques on point-cloud classification. This paper first introduces the principles and characteristics of adversarial attacks and summarizes and analyzes adversarial example generation methods in recent years. Additionally, it provides an overview of defense strategies, organized into data-focused and model-focused methods. Finally, it presents several current challenges and potential future research directions in this domain. INDEX TERMS 3D deep learning, deep neural network, adversarial examples, adversarial defense, machine learning security, 3D point clouds.

show abstract

Section: Datasets and Victim Modelsmentioning

confidence: 99%

Adversarial Attacks and Defenses on 3D Point Cloud Classification: A Survey

Naderi,

Bajić

2023

IEEE Access

Self Cite

View full text Add to dashboard Cite

show abstract

“…In this section, we discuss relevant existing works for 3D shape completion. 3D shape completion works can be categorized into conventional [13,14,15,16,34] and learning-based [5,6,7]. In conventional methods, shape completion is done by considering the geometric cues from the partial input.…”

Section: Related Workmentioning

confidence: 99%

3d Point Cloud Completion Using Stacked Auto-Encoder For Structure Preservation

Kumari

Raman

2021

2021 IEEE International Conference on Image Processing (ICIP)

View full text Add to dashboard Cite

3D point cloud completion problem deals with completing the shape from partial points. The problem finds its application in many visionrelated applications. Here, structure plays an important role. Most of the existing approaches either do not consider structural information or consider structure at the decoder only. For maintaining the structure, it is also necessary to maintain the position of the available 3D points. However, most of the approaches lack the aspect of maintaining the available structural position. In this paper, we propose to employ stacked auto-encoder in conjunction a with shared Multi-Layer Perceptron (MLP). MLP converts each 3D point into a feature vector and the stacked auto-encoder helps in maintaining the available structural position of the input points. Further, it explores the redundancy present in the feature vector. It aids to incorporate coarse to fine scale information that further helps in better shape representation. The embedded feature is finally decoded by a structural preserving decoder. Both the encoding and the decoding operations of our method take care of preserving the structure of the available shape information. The experimental results demonstrate the structure preserving capability of our network as compared to the stateof-the-art methods.

show abstract