77 datasets found

Scene coordinate regression forests for camera relocalization in RGB-D images

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

The dataset used for learning compact geometric features for local geometry in unstructured point clouds.

The Scene Graph Generation (SGG) dataset contains 300,000 images with 10,000 object categories.

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.

A large-scale hierarchical image database for scene recognition.

The VolSDF dataset is used to evaluate the proposed VolSDF method for 3D scene reconstruction.

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

The SUNCG dataset is a large dataset of 3D indoor scenes with missing objects. The dataset is used to evaluate the performance of scene augmentation and context-based object...

The RGB-D scenes dataset contains RGB-D images of indoor scenes with everyday-life objects.

The dataset used in the paper for efficient IoT inference via context-awareness.

Make3D: Learning 3D scene structure from a single still image

Human movement trajectory prediction system that incorporates scene information and human movement trajectories in static crowded scenes.

Scene-15 is a dataset of indoor and outdoor environment images, which consists of 4485 images in total and is divided into 15 categories. It is described by 3 features.

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.

The dataset used in the paper is SUN Attribute, which consists of 717 classes of images with annotations.

A dataset for 3D object detection and scene understanding.

The SEED dataset contains 15 subjects recorded while watching movie clips designated with a negative/neutral/positive emotion label.