Learning of 3D Graph Convolution Networks for Point Cloud Analysis

Lin, Zhihao; Huang, Sheng; Wang, Yu-Chiang Frank

doi:10.1109/tpami.2021.3059758

Cited by 38 publications

(19 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Various point-based convolutional operations [2], [7], [22], [26], [31], [37], [43], [44], [51] were recently proposed to properly capture local context of point clouds. Construction of graph was also suggested in other works [14], [20], [39], [42], [49] for effective point cloud processing. Some studies focused on the speed of pointbased networks, by voxel-based neighbor search [45] or random down-sampling [12].…”

Section: Related Workmentioning

confidence: 99%

Projection-Based Point Convolution for Efficient Point Cloud Segmentation

Ahn

Yang

et al. 2022

IEEE Access

View full text Add to dashboard Cite

Understanding point cloud has recently gained huge interests following the development of 3D scanning devices and the accumulation of large-scale 3D data. Most point cloud processing algorithms can be classified as either point-based or voxel-based methods, both of which have severe limitations in processing time or memory, or both. To overcome these limitations, we propose Projection-based Point Convolution (PPConv), a point convolutional module that uses 2D convolutions and multi-layer perceptrons (MLPs) as its components. In PPConv, point features are processed through two branches: point branch and projection branch. Point branch consists of MLPs, while projection branch transforms point features into a 2D feature map and then apply 2D convolutions. As PPConv does not use point-based or voxelbased convolutions, it has advantages in fast point cloud processing. When combined with a learnable projection and effective feature fusion strategy, PPConv achieves superior efficiency compared to stateof-the-art methods, even with a simple architecture based on PointNet++. We demonstrate the efficiency of PPConv in terms of the trade-off between inference time and segmentation performance. The experimental results on S3DIS and ShapeNetPart show that PPConv is the most efficient method among the compared ones.

show abstract

Section: Related Workmentioning

confidence: 99%

Projection-Based Point Convolution for Efficient Point Cloud Segmentation

Ahn

Yang

et al. 2022

IEEE Access

View full text Add to dashboard Cite

show abstract

“…RSNet [11] adopts a lightweight local dependency module to efficiently model local structures of point clouds. 3D-GCN [20], DGCNN [47], Grid-GCN [53], Spec-Conv [44], SPGraph [16], GAC [45] adopt graph convolutional networks to conduct 3D point cloud learning, while RS-CNN [22], PCNN [3], SCN [51] and KCNet [34] make use of geometric relations for point cloud analysis. Furthermore, SPLATNet [37] uses sparse bilateral convolutional layers to build the network, and SO-Net [18] proposes permutation invariant architectures for learning with unordered point clouds.…”

Section: Related Workmentioning

confidence: 99%

“…The mIoU is obtained by averaging the IoU of all shapes. We compare our model against the state-of-theart point-based methods [14,28,18,51,37,34,11,30,47,3,54,52,20,19,21,49,22], voxel-based methods [6] and the newest point-voxel-based model [23]. To better balance the trade-off between time efficiency and accuracy, we also reduce the output feature channels to 50% and 25%, and marked as MVPCNN (0.5×Ch) and MVPCNN (0.25×Ch) respectively.…”

Section: Part Segmentationmentioning

confidence: 99%

“…Apart from mIoU, mean accuracy (mAcc) is also used to evaluate the performance of our proposed model. In addition to comparing with the state-of-the-art pointbased [28,47,20,11,30,40,56,42,19,53,21,49] and voxel-based methods [6], we also compare with the newest point-voxel-based model [23]. Table 2 shows the results of all methods on S3DIS dataset, and Figure 4…”

Section: Part Segmentationmentioning

confidence: 99%

See 1 more Smart Citation

Multi Voxel-Point Neurons Convolution (MVPConv) for Fast and Accurate 3D Deep Learning

Zhou,

Cao,

Zhang

et al. 2021

Preprint

View full text Add to dashboard Cite

We present a new convolutional neural network, called Multi Voxel-Point Neurons Convolution (MVPConv), for fast and accurate 3D deep learning. The previous works adopt either individual point-based features or local-neighboring voxel-based features to process 3D model, which limits the performance of models due to the inefficient computation. Moreover, most of the existing 3D deep learning frameworks aim at solving one specific task, and only a few of them can handle a variety of tasks. Integrating both the advantages of the voxel and point-based methods, the proposed MVPConv can effectively increase the neighboring collection between point-based features and also promote the independence among voxel-based features. Simply replacing the corresponding convolution module with MVPConv, we show that MVPConv can fit in different backbones to solve a wide range of 3D tasks. Extensive experiments on benchmark datasets such as ShapeNet Part, S3DIS and KITTI for various tasks show that MVPConv improves the accuracy of the backbone (PointNet) by up to 36%, and achieves higher accuracy than the voxel-based model with up to 34× speedup. In addition, MVPConv also outperforms the state-of-the-art point-based models with up to 8× speedup. Notably, our MVPConv achieves better accuracy than the newest point-voxel-based model PVCNN (a model more efficient than PointNet) with lower latency.

show abstract

“…However, it lacked the ability to extract local information, and it was inappropriate to extract the nearest neighbors under the uneven density of point cloud. The point cloud learning networks [32][33][34] under normalized input strongly depend on data sources. The point cloud is affected by the acquisition equipment and the coordinate system, and its arrangement is changeable.…”

mentioning

confidence: 99%

3D Instance Segmentation and Object Detection Framework Based on the Fusion of Lidar Remote Sensing and Optical Image Sensing

Bai

Cen

et al. 2021

Remote Sensing

View full text Add to dashboard Cite

Since single sensor and high-density point cloud data processing have certain direct processing limitations in urban traffic scenarios, this paper proposes a 3D instance segmentation and object detection framework for urban transportation scenes based on the fusion of Lidar remote sensing technology and optical image sensing technology. Firstly, multi-source and multi-mode data pre-fusion and alignment of Lidar and camera sensor data are effectively carried out, and then a unique and innovative network of stereo regional proposal selective search-driven DAGNN is constructed. Finally, using the multi-dimensional information interaction, three-dimensional point clouds with multi-features and unique concave-convex geometric characteristics are instance over-segmented and clustered by the hypervoxel storage in the remarkable octree and growing voxels. Finally, the positioning and semantic information of significant 3D object detection in this paper are visualized by multi-dimensional mapping of the boundary box. The experimental results validate the effectiveness of the proposed framework with excellent feedback for small objects, object stacking, and object occlusion. It can be a remediable or alternative plan to a single sensor and provide an essential theoretical and application basis for remote sensing, autonomous driving, environment modeling, autonomous navigation, and path planning under the V2X intelligent network space– ground integration in the future.

show abstract

Learning of 3D Graph Convolution Networks for Point Cloud Analysis

Cited by 38 publications

References 50 publications

Projection-Based Point Convolution for Efficient Point Cloud Segmentation

Projection-Based Point Convolution for Efficient Point Cloud Segmentation

Multi Voxel-Point Neurons Convolution (MVPConv) for Fast and Accurate 3D Deep Learning

3D Instance Segmentation and Object Detection Framework Based on the Fusion of Lidar Remote Sensing and Optical Image Sensing

Contact Info

Product

Resources

About