18 datasets found

The CAMO dataset contains 3D point clouds of objects from CAD models.

3D shapes are represented as point clouds, which are unordered sets of 3D points.

The McGill 3D dataset used in this paper for testing the generalization of the proposed occupancy learning method.

A dataset of 3D point clouds of human meshes.

Point clouds are 3D point sets containing both geometry coordinates and associated attributes, which can describe scenes correctly and stereoscopically. Recently, point clouds...

Point clouds are 3D point sets containing both geometry coordinates and associated attributes, which can describe scenes correctly and stereoscopically. Recently, point clouds...

A custom dataset created for this paper, consisting of 2107 point clouds, each with 16384 points, and three design point clouds: stripes, porous, and cut.

A dataset of volumetric point clouds for training an autoencoder for point clouds, consisting of four types of point clouds: encapsulated spheres, encapsulated cuboids,...

Deep learning on point clouds has received increased attention thanks to its wide applications in AR/VR and autonomous driving.

The dataset used in the Point2Pix paper, containing point clouds and camera parameters for indoor scenes.

The dataset used in the paper is a collection of unpaired shapes, including chairs and tables, and letters in different font styles.

A large-scale point cloud classification benchmark, focusing on semantic segmentation of urban scenes.

RadHAR dataset

Pantomime dataset

Upper Body Point Cloud Gestures (UBPG) RGB-D gesture point cloud dataset

Gesture recognition interface for point clouds generated by mmWave Radars

The VoxelNet dataset is a large-scale dataset for 3D object detection, consisting of 3D point clouds and corresponding annotations.

Point cloud registration is a crucial problem in computer vision and robotics. Existing methods either rely on matching local geometric features, which are sensitive to the pose...