15 datasets found

Tags: Point Clouds

Filter Results

  • 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.

  • 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.

  • PVT-SSD: Single-Stage 3D Object Detector with Point-Voxel Transformer

    Recent Transformer-based 3D object detectors learn point cloud features either from point- or voxel-based representations.

  • One Million Scenes for Autonomous Driving

    The ONCE dataset is a large-scale dataset for autonomous driving, containing 581 sequences composed of 20 labeled frames and 561 unlabeled frames.

  • CC3D

    A new 3D dataset, CC3D, a collection of 50k+ aligned pairs of meshes, a CAD model and its virtually 3D scanned counterpart with corresponding scanning artifacts.

  • MF

    MF: A proprietary mobile mapping platform dataset.

  • TUM-MLS-2016

    TUM-MLS-2016: An annotated mobile LiDAR dataset of the TUM City Campus for semantic point cloud interpretation in urban areas.

  • SynthCity

    SynthCity: A large scale synthetic point cloud dataset for pre-training deep learning models, enabling generalisation and expansion of their usage to real-world data.

  • MPEG 8i Dataset

    The MPEG 8i dataset contains 6 voxelized point cloud models.

  • Semantic3D

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

  • SEED: A Simple and Effective 3D DETR in Point Clouds

    SEED is a 3D DETR framework for detecting 3D objects from point clouds. It involves a dual query selection module and a deformable grid attention module.

  • VoxelNet

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

  • ScanObjectNN

    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...

  • S3DIS

    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.

  • ModelNet40

    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...