KO
|
EN
gitlite — search
Search
#python
#java
#javascript
#php
#django
#wordpress
#dotfiles
#c-plus-plus
#html
#nodejs
#lua
#symfony
e3d
★ 47
Open GitHub ↗
Efficient 3D Deep Learning
Download README (.md)
Explore Similar Repositories
django-nomadrepo
:
Demo app
flowable-bpmn-modeler
:
本项目基于 vue、ant design vue 和 bpmn.io@7.0 ,实现 flowable 的 modeler 流程设计器
TrafficAnalyzer
:
A simple network traffic analyzer and monitor by Python and Scapy
planetMagFields
:
Routines to plot and analyze magnetic fields of planets in our solar system
catscript
:
No description available.
// repository documentation
Was this content helpful?
★ 0
(0 ratings)
Select Rating:
★
★
★
★
★
Submit Feedback
Recent Feedback
×
Download README
Do you want to download the
README.md
file for
e3d
?
Download (.md)
# Efficient 3D Deep Learning This repo contains our recent advances in efficient 3D point cloud understanding. <img src="https://hanlab.mit.edu/projects/spvnas/figures/overview.png" width="1080"> ## News **[2020-09]** We release baseline training code for SPVCNNs and MinkowskiNets in [SPVNAS](https://github.com/mit-han-lab/spvnas) repo, please have a look! **[2020-08]** Please check out our ECCV 2020 tutorial on [AutoML for Efficient 3D Deep Learning](https://www.youtube.com/watch?v=zzJR07LMXxs), which summarizes the methods released in this codebase. We also made the hands-on tutorial available in colab. **[2020-07]** Our [paper](https://arxiv.org/abs/2007.16100) Searching Efficient 3D Architectures with Sparse Point-Voxel Convolution is accepted to ECCV 2020. **[2020-03]** Our work [PVCNN](https://arxiv.org/abs/1907.03739) is deployed on MIT Driverless racing cars, please check of this [video](https://www.youtube.com/watch?v=WW9paispAW0). **[2019-12]** We give the spotlight talk of [PVCNN](https://arxiv.org/abs/1907.03739) at NeurIPS 2019. ## Projects - [PVCNN](https://github.com/mit-han-lab/pvcnn): Point-Voxel CNN for Efficient 3D Deep Learning - [SPVNAS](https://github.com/mit-han-lab/spvnas): Searching Efficient 3D Architectures with Sparse Point-Voxel Convolution - [TorchSparse](https://github.com/mit-han-lab/torchsparse): High-Performance Neural Network Library for Point Cloud Processing