How this analysis was created: This summary and feature list were written by an AI model that read the project's README and public documentation pages. Each feature links to the documentation it came from; stars, license and language come straight from the GitHub API. The model does not read the source code, and the analysis is refreshed when the project is re-analysed. Learn more on our About page.
This is the release of the code for the paper `Pointwise Convolutional Neural Networks' in CVPR 2018.
SGPN:Similarity Group Proposal Network for 3D Point Cloud Instance Segmentation, CVPR, 2018
SO-Net: Self-Organizing Network for Point Cloud Analysis, CVPR2018
The main features of lijx10/so-net are: Computer Vision Research, Deep Learning Architectures, Segmentation and Classification.
Open-source alternatives to lijx10/so-net include: scenenn/pointwise — This is the release of the code for the paper `Pointwise Convolutional Neural Networks' in CVPR 2018. qianguih/rsnet. ericyi/syncspeccnn. laughtervv/sgpn — SGPN:Similarity Group Proposal Network for 3D Point Cloud Instance Segmentation, CVPR, 2018. nvlabs/splatnet — SPLATNet: Sparse Lattice Networks for Point Cloud Processing (CVPR2018). mvig-sjtu/pointsift.