DESOBAv2: Towards Large-scale Real-world Dataset for Shadow Generation
This work addresses the need for better shadow generation in image composition for computer vision applications, but it is incremental as it extends an existing dataset.
The authors tackled the problem of generating realistic shadows for inserted foreground objects in composite images by creating DESOBAv2, a large-scale dataset built from outdoor scenes using object-shadow detection and inpainting, resulting in a publicly available resource with synthetic composite and ground-truth image pairs.
Image composition refers to inserting a foreground object into a background image to obtain a composite image. In this work, we focus on generating plausible shadow for the inserted foreground object to make the composite image more realistic. To supplement the existing small-scale dataset DESOBA, we create a large-scale dataset called DESOBAv2 by using object-shadow detection and inpainting techniques. Specifically, we collect a large number of outdoor scene images with object-shadow pairs. Then, we use pretrained inpainting model to inpaint the shadow region, resulting in the deshadowed images. Based on real images and deshadowed images, we can construct pairs of synthetic composite images and ground-truth target images. Dataset is available at https://github.com/bcmi/Object-Shadow-Generation-Dataset-DESOBAv2.