Submanifold Sparse Convolutions 3D Semantic Segmentation with Submanifold Sparse Convolutional Networks (arxiv: 1711.10275) Dilation problem 1 nonzero site leads to 3d nonzero sites after 1 convolution How to keep the same level of sparsity throughout the network? 12.. We demonstrate the strong performance of the resulting models, called submanifold sparse convolutional networks (SSCNs), on two tasks involving semantic segmentation of 3D point clouds. In particular, our models outperform all prior state-of-the-art on the test set of a recent semantic segmentation competition.

论文阅读：基于事件的异步稀疏卷积（ECCV 2020） 知乎

稀疏卷积【1】Submanifold Sparse Convolutional NetworksCSDN博客

(PDF) SUBMANIFOLD SPARSE CONVOLUTIONAL NETWORKS FOR SEMANTIC

[PDF] 3D Graph Embedding Learning with a Structureaware Loss Function

[PDF] Submanifold Sparse Convolutional Networks Semantic Scholar

3D Semantic Segmentation with Submanifold Sparse Convolutional Networks

Submanifold Sparse Convolutional Networks

论文阅读：基于事件的异步稀疏卷积（ECCV 2020） 知乎

(PDF) Semantic Segmentation with a Sparse Convolutional Neural Network

3D Semantic Segmentation

Automated Segmentation of Computed Tomography Images with Submanifold

论文阅读：3D Semantic Segmentation with Submanifold Sparse Convolutional

Focal Sparse Convolutional Networks for 3D Object Detection Papers

Submanifold Sparse Convolutional Networks 知乎

3D convolutional neural network (3DCNN) algorithm for segmentation of

Figure 1 from 3D Semantic Segmentation with Submanifold Sparse

3D Semantic Instance Segmentation AI牛丝

阅读笔记[CVPR2018] 3D Semantic Segmentation with Submanifold Sparse

Figure 1 from Multiscale Dynamic Graph Convolutional Network for

Figure 1 from Cosegmentation of Textured 3D Shapes with Sparse

We demonstrate the strong performance of the resulting mod-els, called submanifold sparse convolutional networks (SS-CNs), on two tasks involving semantic segmentation of 3D point clouds. In particular, our models outperform all prior state-of-the-art on the test set of a recent semantic segmen-tation competition. 1.. Convolutional networks are the de-facto standard for analyzing spatio-temporal data such as images, videos, and 3D shapes. Whilst some of this data is naturally dense (e.g., photos), many other data sources are inherently sparse. Examples include 3D point clouds that were obtained using a LiDAR scanner or RGB-D camera. Standard.