# DESOBAv2: Towards Large-scale Real-world Dataset for Shadow Generation

arXiv: https://arxiv.org/abs/2308.09972 · HTML: https://mlsanity.com/paper/2308.09972/

## 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 (most cited first, 6 of 6)

- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [ST-GAN: Spatial Transformer Generative Adversarial Networks for Image Compositing](https://mlsanity.com/paper/1803.01837/) (2018)
- [Shadow Generation for Composite Image in Real-world Scenes](https://mlsanity.com/paper/2104.10338/) (2021)
- [ShadowFormer: Global Context Helps Image Shadow Removal](https://mlsanity.com/paper/2302.01650/) (2023)
- [Instance Shadow Detection with A Single-Stage Detector](https://mlsanity.com/paper/2207.04614/) (2022)
- [What and Where: A Context-based Recommendation System for Object Insertion](https://mlsanity.com/paper/1811.09783/) (2018)

## Built on by (most cited first, 3 of 3)

- [Generative Image Layer Decomposition with Visual Effects](https://mlsanity.com/paper/2411.17864/) (2024)
- [Joint Shadow Generation and Relighting via Light-Geometry Interaction Maps](https://mlsanity.com/paper/2602.21820/) (2026)
- [MultiShadow: Multi-Object Shadow Generation for Image Compositing via Diffusion Model](https://mlsanity.com/paper/2603.02743/) (2026)

## 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.