ORIDa: Object-centric Real-world Image Composition Dataset
Authors:
- 10 June 2025
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 3051-3060
Abstract
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.Keywords
All Related Versions
This publication has 31 references indexed in Scilit:
- FreeCompose: Generic Zero-Shot Image Composition with Diffusion Prior2024
- Diffusion Models are Geometry Critics: Single Image 3D Editing Using Pre-trained Diffusion Priors2024
- Infinite-ID: Identity-Preserved Personalization via ID-Semantics Decoupling Paradigm2024
- ObjectDrop: Bootstrapping Counterfactuals for Photorealistic Object Removal and Insertion2024
- Geometry‐preserved image editingElectronics Letters, 2024
- DCCF: Deep Comprehensible Color Filter Learning Framework for High-Resolution Image Harmonization2022
- Harmonizer: Learning to Perform White-Box Image and Video Harmonization2022
- From Shadow Segmentation to Shadow Removal2020
- Stacked Conditional Generative Adversarial Networks for Jointly Learning Shadow Detection and Shadow Removal2018
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015