52 datasets found

The Waymo Open dataset is a large-scale video dataset used for testing object-centric video models.

The Waymo Domain Adaptation Dataset is a dataset for domain adaptation in 3D object detection, containing 20 sequences with 3933 frames.

A benchmark for 3D object detection in urban environments.

Monocular 3D object detection aims to predict the object location, dimension and orientation in 3D space alongside the object category given only a monocular image.

The KITTI 3D dataset consists of 7,481 images for training and 7,518 images for testing. The labels of the train set are publicly available and the labels of the test set are...

The KITTI benchmark dataset is used to evaluate the performance of the proposed method. The dataset contains large-scale outdoor sequences of images captured by a forward-facing...

The SAM3D dataset is a custom dataset created for the SAM3D paper, containing 798 training sequences, 202 validation sequences, and 150 testing sequences.

The SUNRGB-D dataset features 5,285 training and 5,050 test samples from multiple RGB-D cameras. The dataset provides annotations for the first 37 NYUv2 semantic classes and for...

3D object detection datasets, ScanNet and SUNRGB-D

3D object detection is one of the most important tasks in autonomous driving and robotics. Our research focuses on tackling low efficiency issue of point-based methods on...

The KITTI 3D Object Detection dataset is used for training and testing the proposed Shift R-CNN model.

The Argoverse 3D Tracking Dataset is a large-scale dataset for 3D object detection and road understanding. It contains 3D bounding boxes and tracks annotations, as well as RGB...

3D bounding box estimation using deep learning and geometry.

KITTI-3D benchmark contains a train-ing set of 7481 images and a test set of 7518 images.

The KITTI-360 dataset is an extension of the KITTI dataset, containing 10 new sequences recorded in 2013, with a focus on 360-degree views.

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

The Waymo Open Dataset and the nuScenes Dataset are used to evaluate the performance of the AFDetV2 model.

A widely-adopted multi-modality benchmark for 3D object detection.

A large-scale benchmark for autonomous driving with 1,000 scenes.

The proposed framework for cross-modality 3D object detection, named voxel field fusion.