Object-Placement-Assessment (OPA) is a task consisting on verifying whether a composite image is plausible in terms of the object placement. The foreground object should be placed at a reasonable location on the background considering location, size, occlusion, semantics, and etc.

OPA is a synthesised dataset for Object Placement Assessment based on COCO dataset. The authors selected unoccluded objects from multiple categories as our candidate foreground objects. The foreground objects are pasted on their compatible background images with random sizes and locations to form composite images, which are sent to human annotators for rationality labeling.