Local Spectral Graph Convolution for Point Set Feature Learning

Wang, Chu; Samari, Babak; Siddiqi, Kaleem

doi:10.48550/arxiv.1803.05827

Cited by 14 publications

(16 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[9], [14], [26], [27], [28], [29] define convolution kernels for points with learnable weights, which are similar to image convolution. When the relationships among points have been established, graph convolution [18], [30], [31], [32], [33] can then be applied for local feature learning with high efficiency. Since 3D sensing devices capture points on object surfaces, [15], [34], [35], [36] attempt to operate feature aggregation on surfaces directly and apply 2D CNN or surface CNN instead of in a volumetric way.…”

Section: Related Workmentioning

confidence: 99%

Task-Aware Sampling Layer for Point-Wise Analysis

Lin,

Chen,

Huang

et al. 2021

Preprint

View full text Add to dashboard Cite

Sampling, grouping, and aggregation are three important components in the multi-scale analysis of point clouds. In this paper, we present a novel data-driven sampler learning strategy for point-wise analysis tasks. Unlike the widely used sampling technique, Farthest Point Sampling (FPS), we propose to learn sampling and downstream applications jointly. Our key insight is that uniform sampling methods like FPS are not always optimal for different tasks: sampling more points around boundary areas can make the point-wise classification easier for segmentation. Towards the end, we propose a novel sampler learning strategy that learns sampling point displacement supervised by task-related ground truth information and can be trained jointly with the underlying tasks. We further demonstrate our methods in various point-wise analysis architectures, including semantic part segmentation, point cloud completion, and keypoint detection. Our experiments show that jointly learning of the sampler and task brings remarkable improvement over previous baseline methods.

show abstract

Section: Related Workmentioning

confidence: 99%

Task-Aware Sampling Layer for Point-Wise Analysis

Lin,

Chen,

Huang

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Alternatively, shapes can be treated as graphs by connecting each point to other points within neighborhoods in a feature space. Then graph convolution and pooling operations can be performed either in the spatial domain [1,43,44,45,46,2,47,3,4,5,6,48,15], or spectral domain [49,50,51,52]. Attention mechanisms have also been investigated to modulate the importance of graph edges and point-wise convolutions [33,5,6,7].…”

Section: Related Workmentioning

confidence: 99%

Cross-Shape Attention for Part Segmentation of 3D Point Clouds

Loizou¹,

Petrov²,

Averkiou³

et al. 2020

Preprint

View full text Add to dashboard Cite

We present a method that processes 3D point clouds by performing graph convolution operations across shapes. In this manner, point descriptors are learned by allowing interaction and propagation of feature representations within a shape collection. To enable this form of non-local, cross-shape graph convolution, our method learns a pairwise point attention mechanism indicating the degree of interaction between points on different shapes. Our method also learns to create a graph over shapes of an input collection whose edges connect shapes deemed as useful for performing cross-shape convolution. The edges are also equipped with learned weights indicating the compatibility of each shape pair for cross-shape convolution. Our experiments demonstrate that this interaction and propagation of point representations across shapes makes them more discriminative. In particular, our results show significantly improved performance for 3D point cloud semantic segmentation compared to conventional approaches, especially in cases with limited number of training examples.

show abstract

“…The second category is a view-based method [20,15], which projects the 3D shape onto a 2D image such that more classical 2D approaches can be utilized. The third category uses raw point cloud data as input which the network then operates on directly [16,23,12,25,22]. In this work, we focus on 3D object classification based on the latter, raw point cloud representation.…”

Section: Related Workmentioning

confidence: 99%

“…Some methods, in turn, instead improve the aggregation module of PointNet [14]. [22] proposes a structure similar to PointNet++ [16] but replaces the mini-pointnet with a spectral convolution operation. To achieve this, a new pooling method, called Recursive cluster pooling is introduced.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

3DCapsule: Extending the Capsule Architecture to Classify 3D Point Clouds

Cheraghian

2019

2019 IEEE Winter Conference on Applications of Computer Vision (WACV)

View full text Add to dashboard Cite

This paper introduces the 3DCapsule, which is a 3D extension of the recently introduced Capsule concept that makes it applicable to unordered point sets. The original Capsule relies on the existence of a spatial relationship between the elements in the feature map it is presented with, whereas in point permutation invariant formulations of 3D point set classification methods, such relationships are typically lost. Here, a new layer called ComposeCaps is introduced that, in lieu of a spatially relevant feature mapping, learns a new mapping that can be exploited by the 3DCapsule. Previous works in the 3D point set classification domain have focused on other parts of the architecture, whereas instead, the 3DCapsule is a drop-in replacement of the commonly used fully connected classifier. It is demonstrated via an ablation study, that when the 3DCapsule is applied to recent 3D point set classification architectures, it consistently shows an improvement, in particular when subjected to noisy data. Similarly, the ComposeCaps layer is evaluated and demonstrates an improvement over the baseline. In an apples-to-apples comparison against state-ofthe-art methods, again, better performance is demonstrated by the 3DCapsule.

show abstract

Local Spectral Graph Convolution for Point Set Feature Learning

Cited by 14 publications

References 11 publications

Task-Aware Sampling Layer for Point-Wise Analysis

Task-Aware Sampling Layer for Point-Wise Analysis

Cross-Shape Attention for Part Segmentation of 3D Point Clouds

3DCapsule: Extending the Capsule Architecture to Classify 3D Point Clouds

Contact Info

Product

Resources

About