-
Waymo Open
The Waymo Open dataset is a large-scale video dataset used for testing object-centric video models. -
STPLS3D: A large-scale synthetic and real aerial photogrammetry 3D point clou...
STPLS3D: A large-scale synthetic and real aerial photogrammetry 3D point cloud dataset -
3DRIMR: 3D Reconstruction and Imaging via mmWave Radar
Real and synthesized mmWave radar data, ground truth 2D depth images and point clouds for 3DRIMR experiments -
Surface Reconstruction Benchmark
The dataset used in the paper for surface reconstruction from point clouds. -
Neural Gas dataset
The dataset used in the paper is a collection of 2D and 3D point clouds, each representing a different shape (e.g. unit circle, unit disk, unit sphere, unit ball, Stanford... -
Mip-NeRF 360 and Tanks & Temples datasets
The Mip-NeRF 360 and Tanks & Temples datasets are used to evaluate the performance of the Pixel-GS method. -
Uni3DL: Unified Model for 3D and Language Understanding
Uni3DL is a unified model for 3D and language understanding. It operates directly on point clouds and supports diverse 3D vision-language tasks, including semantic segmentation,... -
Thingi10k dataset
A dataset of 1000 3D models, used for testing the robustness of surface reconstruction methods. -
TUM City Campus Dataset
TUM-MLS-2016: An annotated mobile lidar dataset of the TUM City Campus for semantic point cloud interpretation in urban areas. -
University of Sydney Campus Dataset
Developing and testing robust autonomy: The university of sydney campus data set. -
3D ShapeNets
3D ShapeNets: A Deep Representation for Volumetric Shapes. -
Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling
Point-BERT is a new paradigm for learning point cloud Transformers. It pre-trains standard point cloud Transformers with a Masked Point Modeling (MPM) task. -
PartNet and ScanNet
Semantic segmentation and 3D detection tasks on PartNet and ScanNet datasets -
ScanNet and SUNRGB-D
3D object detection datasets, ScanNet and SUNRGB-D -
ULIP: Unified Representation of Language, Images, and Point Clouds
ULIP: Learning a unified representation of language, images, and point clouds for 3D understanding -
ModelNet dataset
The dataset used for training a Convolutional Neural Network to predict a grasp quality score over all grasp poses, given a depth image of an object. -
Argoverse 2
The Argoverse 2 motion forecasting dataset contains 250,000 driving scenarios, each 11 seconds long. These scenarios cover 6 geographical regions and represent 763 total hours... -
Point-Cloud Deep Learning Framework for Prediction of Fluid Flow Fields on Ir...
A Point-Cloud Deep Learning Framework for Prediction of Fluid Flow Fields on Irregular Geometries
