65 datasets found

Data-driven Instruction Augmentation for Language-conditioned Control (DIAL) is a method that uses pre-trained vision-language models (VLMs) to label offline datasets for...

The Vision-and-Language Navigation (VLN) task gives a global natural sentence I = {w0,..., wl} as an instruction, where wi is a word token while the l is the length of the...

Two novel datasets are created using the ARS pipeline, one on electromechanical components (industrial scenario) and one on fruits (daily-living scenario).

A synthetic dataset of shoes for training and testing the proposed method.

A unified object-centric implicit representation that can be used for RGB and depth novel view rendering, 3D reconstruction, and proposing stable grasps.

Depth prediction is fundamental for many useful applications on computer vision and robotic systems. On mobile phones, the performance of some useful applications as augmented...

The dataset used in the paper is a collection of images of objects in 3D space, with multiple views of each object.

The dataset used in the paper is a collection of images of objects in 3D space, with multiple views of each object.

The dataset used in the paper is a collection of images of objects in 3D space, with multiple views of each object.

The Oxford RobotCar Dataset is a collection of images and videos of a car driving on various roads and conditions.

The dataset used for training and testing the direct regression model, sparse correspondence model, and dense correspondence model.

The dataset used for learning-based methods for online eye-in-hand camera calibration from a single RGB image.

PhotoBot is a framework for fully automated photo acquisition based on an interplay between high-level human language guidance and a robot photographer.

The Sunny Test Dataset is used for testing, it contains 2114 images from nine distinct rooms.

The Night Test Dataset is used for testing, it contains 2707 images from nine distinct rooms.

The Cloudy Test Dataset is used for testing, it contains 2595 images from nine distinct rooms.

The Validation Dataset is used for validation, it contains 1428 images from nine distinct rooms.

The Baseline Training Dataset is used for training the CNN model, it contains 556 images from nine distinct rooms.

The COLD Freiburg Database contains omnidirectional images captured by a robot which follows various paths within a building at Freiburg University.

GraspNet-1Billion is a large-scale real-world grasping dataset containing 190 cluttered grasping scenes and 97,280 RGB-D images captured by 2 kinds of RGB-D cameras from 256...