facebookresearch/votenet

Health v2 · maintenance only

Flags: no_releases archived

Adoption not part of the score

1761 stars · 388 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

VoteNet is the official PyTorch implementation of the ICCV 2019 paper 'Deep Hough Voting for 3D Object Detection in Point Clouds'. It provides an end-to-end 3D object detection network combining deep point set networks with Hough voting, plus data preparation, training, and evaluation scripts for SUN RGB-D and ScanNet datasets.

Use cases

• detect 3D bounding boxes in point clouds
• train a 3D object detection model on ScanNet
• evaluate 3D detection on SUN RGB-D
• reproduce ICCV 2019 VoteNet paper results
• benchmark 3D detectors using only geometry without RGB images
• build robotics perception on indoor 3D scans

When to choose

• you need pure-geometry 3D object detection from point clouds
• you want a compact, efficient reference model for ScanNet or SUN RGB-D
• you are doing research on point cloud detection and want a strong baseline

When to avoid

• you need actively maintained code with modern PyTorch/CUDA versions
• you need RGB-image-based or LiDAR outdoor detection (e.g., KITTI/nuScenes)
• you want a production-ready detection pipeline rather than research code

Facets

library · maturity maintenance

machine-learning deep-learning computer-vision image-processing computer-vision robotics deep-learning machine-learning python 3d-object-detection point-cloud hough-voting pytorch research-code scannet sun-rgbd linux gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="facebookresearch/votenet")