31 datasets found

Establishing both accurate and robust correspondences across images is an underpinning step to many computer vision algorithms.

A dataset for evaluating the performance of image tampering detection methods.

The Playroom is a Unity-based environment for object-centric tasks [69, 46], originally released as pre-packaged Docker containers with an Apache 2.0 license.

Objects Room was a MuJoCo-based dataset originally released under the Apache 2.0 license and used for prior work such as GQN and MONet.

The dataset used in the paper is a simulated dataset for scene understanding and planning tasks, containing images of objects and scenes.

The dataset used in the paper is a simulated dataset for scene understanding and planning tasks, containing images of objects and scenes.

COCOStuff is a scene-centric dataset with a total of 80 things and 91 stuff categories.

ETH3D is a small real-world grayscale dataset with both indoor and outdoor scenes. It contains 27 labeled stereo image pairs for training and 20 stereo pairs for testing.

A dataset for 3D object detection and scene understanding.

The NYU Depth dataset is a large-scale dataset of indoor and outdoor scenes, which is widely used for 3D depth estimation and scene understanding tasks.

The PASCAL-Context and NYUD-v2 datasets are used for multi-task learning in dense scene understanding.

A dataset for urban scene understanding.

The dataset used in the paper is a multi-view clustering dataset, which contains 6 views of 2000 samples each. The dataset is used to evaluate the performance of the proposed...

A dataset for layout annotation of Matterport3D images.

The COCO-stuff dataset is a large-scale dataset for scene understanding, object detection, and image synthesis.

The dataset used in the paper is a collection of images of objects with varying viewpoints, used for training and testing the proposed RRB framework.

The Sketchy dataset contains sketches of objects and scenes

A dataset for indoor scene understanding, containing 1449 RGBD images.

The authors used the RefCOCO dataset, a large-scale dataset for object detection and scene understanding, to train and evaluate their models.

The ADE-20k dataset, which is a benchmark for semantic understanding of scenes.