Active 3D Classification of Multiple Objects in Cluttered Scenes

Wang, Yiming; Carletti, Marco; Setti, Francesco; Cristani, Marco; Bue, Alessio Del

doi:10.1109/iccvw.2019.00318

Cited by 7 publications

(1 citation statement)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…1. Instead of performing such PCD-level integration for shape recognition [8], we propose PointView-GCN, to aggregate the shape features from the multi-view partial PCDs in order to further exploit the relations among multiple views in the feature space. With experiments on both synthetic [9] and real-world datasets [10], we prove that PointView-GCN is able to produce a Fig.…”

Section: Introductionmentioning

confidence: 99%

Pointview-GCN: 3D Shape Classification With Multi-View Point Clouds

Mohammadi¹,

Wang

Bue

2021

2021 IEEE International Conference on Image Processing (ICIP)

Self Cite

View full text Add to dashboard Cite

We address 3D shape classification with partial point cloud inputs captured from multiple viewpoints around the object. Different from existing methods that perform classification on the complete point cloud by first registering multi-view capturing, we propose PointView-GCN with multi-level Graph Convolutional Networks (GCNs) to hierarchically aggregate the shape features of single-view point clouds, in order to encode both the geometrical cues of an object and their multiview relations. With experiments on our novel single-view datasets, we prove that PointView-GCN produces a more descriptive global shape feature which stably improves the classification accuracy by ∼ 5% compared to the classifiers with single-view point clouds, and outperforms the state-of-the-art methods with the complete point clouds on ModelNet40.

show abstract

Section: Introductionmentioning

confidence: 99%

Pointview-GCN: 3D Shape Classification With Multi-View Point Clouds

Mohammadi¹,

Wang

Bue

2021

2021 IEEE International Conference on Image Processing (ICIP)

Self Cite

View full text Add to dashboard Cite

show abstract

SVP-Classifier: Single-View Point Cloud Data Classifier with Multi-view Hallucination

Mohammadi

Wang

Taiana

et al. 2022

Image Analysis and Processing – ICIAP 2022

View full text Add to dashboard Cite

Unsupervised Point Cloud Representation Learning by Clustering and Neural Rendering

Mei,

Saltori,

Ricci

et al. 2024

Int J Comput Vis

View full text Add to dashboard Cite

Data augmentation has contributed to the rapid advancement of unsupervised learning on 3D point clouds. However, we argue that data augmentation is not ideal, as it requires a careful application-dependent selection of the types of augmentations to be performed, thus potentially biasing the information learned by the network during self-training. Moreover, several unsupervised methods only focus on uni-modal information, thus potentially introducing challenges in the case of sparse and textureless point clouds. To address these issues, we propose an augmentation-free unsupervised approach for point clouds, named CluRender, to learn transferable point-level features by leveraging uni-modal information for soft clustering and cross-modal information for neural rendering. Soft clustering enables self-training through a pseudo-label prediction task, where the affiliation of points to their clusters is used as a proxy under the constraint that these pseudo-labels divide the point cloud into approximate equal partitions. This allows us to formulate a clustering loss to minimize the standard cross-entropy between pseudo and predicted labels. Neural rendering generates photorealistic renderings from various viewpoints to transfer photometric cues from 2D images to the features. The consistency between rendered and real images is then measured to form a fitting loss, combined with the cross-entropy loss to self-train networks. Experiments on downstream applications, including 3D object detection, semantic segmentation, classification, part segmentation, and few-shot learning, demonstrate the effectiveness of our framework in outperforming state-of-the-art techniques.

show abstract

Active 3D Classification of Multiple Objects in Cluttered Scenes

Cited by 7 publications

References 32 publications

Pointview-GCN: 3D Shape Classification With Multi-View Point Clouds

Pointview-GCN: 3D Shape Classification With Multi-View Point Clouds

SVP-Classifier: Single-View Point Cloud Data Classifier with Multi-view Hallucination

Unsupervised Point Cloud Representation Learning by Clustering and Neural Rendering

Contact Info

Product

Resources

About