ORIDa: Object-centric Real-world Image Composition Dataset
This provides a resource for researchers in computer vision working on object compositing, though it is incremental as it focuses on dataset creation rather than a new method.
The authors tackled the lack of diverse and large-scale datasets for object compositing by introducing ORIDa, a dataset with over 30,000 images and 200 unique objects across varied scenes, which they claim is the first of its kind for real-world image composition.
Object compositing, the task of placing and harmonizing objects in images of diverse visual scenes, has become an important task in computer vision with the rise of generative models. However, existing datasets lack the diversity and scale required to comprehensively explore real-world scenarios. We introduce ORIDa (Object-centric Real-world Image Composition Dataset), a large-scale, real-captured dataset containing over 30,000 images featuring 200 unique objects, each of which is presented across varied positions and scenes. ORIDa has two types of data: factual-counterfactual sets and factual-only scenes. The factual-counterfactual sets consist of four factual images showing an object in different positions within a scene and a single counterfactual (or background) image of the scene without the object, resulting in five images per scene. The factual-only scenes include a single image containing an object in a specific context, expanding the variety of environments. To our knowledge, ORIDa is the first publicly available dataset with its scale and complexity for real-world image composition. Extensive analysis and experiments highlight the value of ORIDa as a resource for advancing further research in object compositing.