DESOBAv2: Towards Large-scale Real-world Dataset for Shadow Generation
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 6 of its 10 references that are in the map. First posted on arXiv 19 Aug 2023.
Builds on
6 of 10 references.
References · 6
- 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
- 2018ST-GAN: Spatial Transformer Generative Adversarial Networks for Image Compositingcited by 90
- 2021Shadow Generation for Composite Image in Real-world Scenescited by 35
- 2023ShadowFormer: Global Context Helps Image Shadow Removalcited by 35
- 2022Instance Shadow Detection with A Single-Stage Detectorcited by 22
- 2018What and Where: A Context-based Recommendation System for Object Insertioncited by 14
Built on by
Citing papers per year: 2024: 1; 2025: 0; 2026: 2.
3 papers.