facebookresearch/votenet

Deep Hough Voting for 3D Object Detection in Point Clouds

Archived
51
/ 100
Established

Combines PointNet++ backbone with Hough voting to overcome the challenge of regressing object centroids from sparse point cloud surfaces, eliminating the need for voxelization or multi-view conversion. Implemented in PyTorch with CUDA-optimized layers, supporting end-to-end training on SUN RGB-D and ScanNet datasets using only geometric information without RGB data.

1,751 stars. No commits in the last 6 months.

Archived Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 25 / 25

How are scores calculated?

Stars

1,751

Forks

386

Language

Python

License

MIT

Category

point-cloud-processing

Last pushed

Jan 30, 2022

Commits (30d)

0

GitHub
Point Cloud Processing · 37 tools

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/facebookresearch/votenet"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.

Related tools

drprojects/superpoint_transformer

Official PyTorch implementation of Superpoint Transformer introduced in [ICCV'23] "Efficient 3D...

58

yuxumin/PoinTr

[ICCV 2021 Oral] PoinTr: Diverse Point Cloud Completion with Geometry-Aware Transformers

55

drprojects/DeepViewAgg

[CVPR'22 Best Paper Finalist] Official PyTorch implementation of the method presented in...

51

charlesq34/frustum-pointnets

Frustum PointNets for 3D Object Detection from RGB-D Data

51

Easonyesheng/A2PM-MESA

[CVPR'24 & TPAMI'26] Area to Point Matching Framework

50

Explore Computer Vision Tools

All categories Trending Computer Vision directory Insights