VoteNet is a 3D object detection framework for point clouds that combines deep point set networks with a Hough voting mechanism to localize and classify objects in 3D space. It tackles the challenge that object centroids in 3D scenes often don’t lie on any input surface point by having each point “vote” for potential object centers; these votes are then clustered to propose object hypotheses. Once cluster centers are formed, the network regresses bounding boxes around them and classifies them. VoteNet works end-to-end: it learns the voting, aggregation, and bounding-box regression components jointly, enabling strong detection accuracy without relying on 2D proxies or voxelization. The codebase includes data preparation for indoor datasets (SUN RGB-D, ScanNet), training and evaluation scripts, and demo utilities to visualize predicted boxes over point clouds.
Features
- Deep point set backbone (e.g. PointNet++) to extract features from raw point clouds
- Hough voting module: points propose object centers to overcome centroid regression challenges
- Clustering of votes to form object proposals and bounding box regression
- Joint end-to-end training of voting, regression, and classification heads
- Preprocessing, training, and evaluation scripts for SUN RGB-D and ScanNet datasets
- Visualization tools for rendering point clouds with predicted boxes
Project Samples
