18 datasets found

The dataset used in the paper is a 3D point cloud compression dataset, consisting of four sequences: longdress, redandblack, loot and soldier. Each sequence contains 300 frames.

An urban-scale photogrammetric point cloud dataset with nearly three billion richly annotated points, covering about 7.6 km2 of the city landscape.

Synth4D is a dataset of 20,000 LiDAR point clouds synthesized by the CARLAsimulator.

3D point cloud segmentation has received significant interest for its growing applications. However, the generalization ability of models suffers in dynamic scenarios due to the...

The dataset used to test the proposed region-growing-based algorithm for automatic extraction of outcrop fractures from 3D point clouds.

The dataset used for indoor scene segmentation and object part segmentation.

The PointNet dataset is used for semantic segmentation of 3D point clouds. It contains annotated point clouds of objects such as table, human, box, robot, and cube.

The dataset used in this paper is a 120m×120m×20m indoor environment.

The dataset used in this paper is a 120m×120m×20m outdoor environment consisting of a ground and multiple irregular 3D buildings.

The Business District dataset is a dataset of 3D point clouds of business districts.

The Residential Area dataset is a dataset of 3D point clouds of residential areas.

The University Sector dataset is a dataset of 3D point clouds of university buildings.

The Argoverse dataset is a large-scale dataset for autonomous driving, containing 3D point clouds, semantic segmentation masks, and instance segmentation masks.

Zero-shot learning (ZSL) aims to classify objects that are not observed or seen during training. It relies on class semantic description to transfer knowledge from the seen...

A point cloud dataset with large quantity of dynamic instances, consisting of 2,988 real-world scans with point-level annotations.

The S3DIS and ScanNet datasets are used for point cloud semantic segmentation.

The dataset used in the paper is a real-world 3D point cloud dataset, which is used for 3D shape classification, part segmentation, and shape retrieval tasks.

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...