Custom traffic gesture dataset containing measurements of eight different gestures for 35 participants.

The dataset used in the paper is the NuScenes dataset, which contains LiDAR point clouds and corresponding semantic annotations.

KITTI 2012 is a real-world dataset in the outdoor scenario, and contains 194 training and 195 testing stereo image pairs with the size of 376 × 1240.

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

The proposed method extracts a complete lane graph from a single onboard camera image. It uses a transformer-based Wasserstein Autoencoder to process a lane graph and produce a...

The CARLA dataset is a complex urban-like environment with multi-agent dynamics, pedestrians, intersections, cross-traffic, roundabout, and changing weather conditions.

The KITTI Vision Benchmark Suite is a dataset used for object detection and tracking in autonomous vehicles.

The KITTI object detection benchmark dataset.

The TrafficGen dataset is a collection of traffic scenarios generated using a generative model.

The Bi-Level Imitation Learning System (BITS) is a model that utilizes a two-tiered imitation learning strategy for traffic prediction tasks.

The Conditional Traffic Generation (CTG) model is a state-of-the-art model for controllable traffic simulation.

SODA10M contains 10M un-labeled images and 20K labeled images of size 1920 × 1080 with default format of JPEG.

The MVSEC dataset is a dataset for event-based camera data, featuring 5 sequences of a car on the street, as well as 4 short indoor sequences shot from a flying quadrotor.

The Waymo Open Motion Dataset is a large-scale dataset for autonomous driving, containing 104,000 20-second frames of driving scenarios marked at 10 Hz.

The dataset used in the paper is the KITTI dataset, which is a benchmark for monocular depth estimation. The dataset consists of a large collection of images and corresponding...

The KITTI 2015 dataset is a real-world dataset of street views, containing 200 training stereo image pairs with sparsely labeled disparity from LiDAR data.