# Shadow Generation with Decomposed Mask Prediction and Attentive Shadow Filling

arXiv: https://arxiv.org/abs/2306.17358 · HTML: https://mlsanity.com/paper/2306.17358/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Jun 2023.

## Built on by (most cited first, 8 of 8)

- [Shadow Generation for Composite Image Using Diffusion model](https://mlsanity.com/paper/2403.15234/) (2024)
- [Single-Image Shadow Removal Using Deep Learning: A Comprehensive Survey](https://mlsanity.com/paper/2407.08865/) (2024)
- [Refracting Reality: Generating Images with Realistic Transparent Objects](https://mlsanity.com/paper/2511.17340/) (2025)
- [FastInstShadow: A Simple Query-Based Model for Instance Shadow Detection](https://mlsanity.com/paper/2503.07517/) (2025)
- [KPLM-STA: Physically-Accurate Shadow Synthesis for Human Relighting via Keypoint-Based Light Modeling](https://mlsanity.com/paper/2511.08169/) (2025)
- [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)
- [VSDiffusion: Taming Ill-Posed Shadow Generation via Visibility-Constrained Diffusion](https://mlsanity.com/paper/2603.08020/) (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 shadows for the inserted foreground object to make the composite image more realistic. To supplement the existing small-scale dataset, we create a large-scale dataset called RdSOBA with rendering techniques. Moreover, we design a two-stage network named DMASNet with decomposed mask prediction and attentive shadow filling. Specifically, in the first stage, we decompose shadow mask prediction into box prediction and shape prediction. In the second stage, we attend to reference background shadow pixels to fill the foreground shadow. Abundant experiments prove that our DMASNet achieves better visual effects and generalizes well to real composite images.