34 datasets found

Self-supervised adversarial masking for 3D point cloud representation learning

The A9-Intersection dataset is a real-world dataset made of two RSUs positioned at 7 meters height in an intersection in Garching, Germany. Each RSU has an Ouster OS1-64 LiDAR...

The V2X-Sim 2.0 dataset is a synthetic dataset made with CARLA, containing 100 sequences, each of which has 100 samples containing point clouds obtained by 1 RSU positioned at...

The dataset used in the paper is a synthetic dataset of 3D point clouds with polyhedral wireframe annotations.

Instance segmentation on 3D point clouds is one of the most extensively researched areas toward the realization of autonomous cars and robots.

Instance segmentation on 3D point clouds is one of the most extensively researched areas toward the realization of autonomous cars and robots.

The PointSegDA dataset is a benchmark dataset for point cloud segmentation.

The PointDA-10 dataset consists of three subsets of three widely-used datasets: ShapeNet, ModelNet, and ScanNet. All three subsets share the same ten distinct classes.

The dataset used in the paper is ModelNet40-C, which is a 3D point cloud dataset with various corruptions.

The dataset used in the paper is ModelNet40 and ModelNet40-C, which are 3D point cloud datasets.

The dataset used in this paper for 3D point cloud classification and adversarial example generation.

The FastDiT-3D dataset is a dataset of 3D point clouds, consisting of 3,000 models, each described by 2,048 points.

The DiT-3D dataset is a dataset of 3D point clouds, consisting of 3,000 models, each described by 2,048 points.

The PVD dataset is a dataset of 3D point clouds, consisting of 3,000 models, each described by 2,048 points.

The Synthia dataset is a driving scenario dataset containing 6 video sequences in 9 different weather environments.

The MSRAction3D dataset contains 567 Kinect depth map sequences from 10 people with 20 actions.

The dataset used in the paper is ScanNetV2, a real-world dataset for indoor scenes. It contains 1205 training scenes and 312 testing scenes, with instance-level object bounding...

The 2D-3D-S dataset is an indoor dataset with multiple modalities from 2D, 2.5D and 3D domains, with instance-level semantic and geometric annotations.

The ModelNet-10 dataset is a benchmark for 3D point cloud classification and semantic segmentation. It contains 4,899 untextured CAD models divided into 10 categories.

The dataset used in this paper is a collection of 3D point clouds.