7 datasets found

Image generation from scene graphs is a task in computer vision that requires generating images from graph-structured inputs, such as scene graphs.

Generating images from graph-structured inputs, such as scene graphs, is uniquely challenging due to the difficulty of aligning nodes and connections in graphs with objects and...

The 3D scene graph dataset contains 3D scene graphs with semantic entities, attributes, and relationships.

The 3RScan dataset contains 3D point clouds captured over time along with their 3D scene graph annotations.

A multiple relations scene graph-image paired dataset with highly precise labels called MultiRels.

Text-conditioned image generation has made significant progress in recent years with generative adversarial networks and more recently, diffusion models. The proposed guidance...

The Visual Genome dataset is a large-scale visual question answering dataset, containing 1.5 million images, each with 15-30 annotated entities, attributes, and relationships.