GitPlanet

Cheap and reliable Node.js hosting starts at $3/month, and $1/month static HTML hosting

Created with love in Canada, visit hostnodejs.com today

Feel like to post an Ad? Learn Details
All Projects → mit-han-lab → e3d

mit-han-lab / e3d

Licence: other
Efficient 3D Deep Learning

Labels

deep-learningpoint-cloud3d-perception

Projects that are alternatives of or similar to e3d

FLAT
[ICCV2021 Oral] Fooling LiDAR by Attacking GPS Trajectory
Stars: ✭ 52 (+18.18%)
Mutual labels:  point-cloud, 3d-perception
pointcloud viewer
No description or website provided.
Stars: ✭ 16 (-63.64%)
Mutual labels:  point-cloud
Point Cloud Annotation Tool
Stars: ✭ 224 (+409.09%)
Mutual labels:  point-cloud
Scan2Cap
[CVPR 2021] Scan2Cap: Context-aware Dense Captioning in RGB-D Scans
Stars: ✭ 81 (+84.09%)
Mutual labels:  point-cloud
Cylinder3d
Rank 1st in the leaderboard of SemanticKITTI semantic segmentation (both single-scan and multi-scan) (Nov. 2020) (CVPR2021 Oral)
Stars: ✭ 221 (+402.27%)
Mutual labels:  point-cloud
SGGpoint
[CVPR 2021] Exploiting Edge-Oriented Reasoning for 3D Point-based Scene Graph Analysis (official pytorch implementation)
Stars: ✭ 41 (-6.82%)
Mutual labels:  point-cloud
Cgal
The public CGAL repository, see the README below
Stars: ✭ 2,825 (+6320.45%)
Mutual labels:  point-cloud
superpose3d
register 3D point clouds using rotation, translation, and scale transformations.
Stars: ✭ 34 (-22.73%)
Mutual labels:  point-cloud
UnsupervisedPointCloudReconstruction
Experiments on unsupervised point cloud reconstruction.
Stars: ✭ 133 (+202.27%)
Mutual labels:  point-cloud
Flownet3d
FlowNet3D: Learning Scene Flow in 3D Point Clouds (CVPR 2019)
Stars: ✭ 249 (+465.91%)
Mutual labels:  point-cloud
Spvnas
[ECCV 2020] Searching Efficient 3D Architectures with Sparse Point-Voxel Convolution
Stars: ✭ 239 (+443.18%)
Mutual labels:  point-cloud
Cupoch
Robotics with GPU computing
Stars: ✭ 225 (+411.36%)
Mutual labels:  point-cloud
Displaz.jl
Julia bindings for the displaz lidar viewer
Stars: ✭ 16 (-63.64%)
Mutual labels:  point-cloud
Pointnetvlad
PointNetVLAD: Deep Point Cloud Based Retrieval for Large-Scale Place Recognition, CVPR 2018
Stars: ✭ 224 (+409.09%)
Mutual labels:  point-cloud
SpareNet
Style-based Point Generator with Adversarial Rendering for Point Cloud Completion (CVPR 2021)
Stars: ✭ 118 (+168.18%)
Mutual labels:  point-cloud
Kitti Dataset
Visualising LIDAR data from KITTI dataset.
Stars: ✭ 217 (+393.18%)
Mutual labels:  point-cloud
Pcn
Code for PCN: Point Completion Network in 3DV'18 (Oral)
Stars: ✭ 238 (+440.91%)
Mutual labels:  point-cloud
ldgcnn
Linked Dynamic Graph CNN: Learning through Point Cloud by Linking Hierarchical Features
Stars: ✭ 66 (+50%)
Mutual labels:  point-cloud
3D Ground Segmentation
A ground segmentation algorithm for 3D point clouds based on the work described in “Fast segmentation of 3D point clouds: a paradigm on LIDAR data for Autonomous Vehicle Applications”, D. Zermas, I. Izzat and N. Papanikolopoulos, 2017. Distinguish between road and non-road points. Road surface extraction. Plane fit ground filter
Stars: ✭ 55 (+25%)
Mutual labels:  point-cloud
attMPTI
[CVPR 2021] Few-shot 3D Point Cloud Semantic Segmentation
Stars: ✭ 118 (+168.18%)
Mutual labels:  point-cloud
View All Similar Projects ➔

Efficient 3D Deep Learning

This repo contains our recent advances in efficient 3D point cloud understanding.

News

[2020-09] We release baseline training code for SPVCNNs and MinkowskiNets in SPVNAS repo, please have a look!

[2020-08] Please check out our ECCV 2020 tutorial on AutoML for Efficient 3D Deep Learning, which summarizes the methods released in this codebase. We also made the hands-on tutorial available in colab.

[2020-07] Our paper Searching Efficient 3D Architectures with Sparse Point-Voxel Convolution is accepted to ECCV 2020.

[2020-03] Our work PVCNN is deployed on MIT Driverless racing cars, please check of this video.

[2019-12] We give the spotlight talk of PVCNN at NeurIPS 2019.

Projects

  • PVCNN: Point-Voxel CNN for Efficient 3D Deep Learning
  • SPVNAS: Searching Efficient 3D Architectures with Sparse Point-Voxel Convolution
  • TorchSparse: High-Performance Neural Network Library for Point Cloud Processing
Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].