# MultiShadow: Multi-Object Shadow Generation for Image Compositing via Diffusion Model

arXiv: https://arxiv.org/abs/2603.02743 · HTML: https://mlsanity.com/paper/2603.02743/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in 3D, point cloud and scene generation, one of 14 directions in Diffusion models.
- Builds on 20 of its 30 references that are in the map.
- First posted on arXiv 3 Mar 2026.

## Placed in

- Diffusion models / [3D, point cloud and scene generation](https://mlsanity.com/diffusion/3d-point-cloud-and-scene-generation/)

## Builds on (most cited first, 20 of 20)

- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [GLIGEN: Open-Set Grounded Text-to-Image Generation](https://mlsanity.com/paper/2301.07093/) (2023)
- [Paint by Example: Exemplar-based Image Editing with Diffusion Models](https://mlsanity.com/paper/2211.13227/) (2022)
- [LayoutDiffusion: Controllable Diffusion Model for Layout-to-image Generation](https://mlsanity.com/paper/2303.17189/) (2023)
- [ReCo: Region-Controlled Text-to-Image Generation](https://mlsanity.com/paper/2211.15518/) (2022)
- [ViP-LLaVA: Making Large Multimodal Models Understand Arbitrary Visual Prompts](https://mlsanity.com/paper/2312.00784/) (2023)
- [Making Images Real Again: A Comprehensive Survey on Deep Image Composition](https://mlsanity.com/paper/2106.14490/) (2021)
- [ObjectStitch: Generative Object Compositing](https://mlsanity.com/paper/2212.00932/) (2022)
- [Shadow Generation for Composite Image in Real-world Scenes](https://mlsanity.com/paper/2104.10338/) (2021)
- [SSN: Soft Shadow Network for Image Compositing](https://mlsanity.com/paper/2007.08211/) (2020)
- [Instance Shadow Detection with A Single-Stage Detector](https://mlsanity.com/paper/2207.04614/) (2022)
- [Shadow Generation for Composite Image Using Diffusion model](https://mlsanity.com/paper/2403.15234/) (2024)
- [PixHt-Lab: Pixel Height Based Light Effect Generation for Image Compositing](https://mlsanity.com/paper/2303.00137/) (2023)
- [Uncovering the Text Embedding in Text-to-Image Diffusion Models](https://mlsanity.com/paper/2404.01154/) (2024)
- [Multitwine: Multi-Object Compositing with Text and Layout Control](https://mlsanity.com/paper/2502.05165/) (2025)
- [Shadow Generation with Decomposed Mask Prediction and Attentive Shadow Filling](https://mlsanity.com/paper/2306.17358/) (2023)
- [MetaShadow: Object-Centered Shadow Detection, Removal, and Synthesis](https://mlsanity.com/paper/2412.02635/) (2024)
- [DESOBAv2: Towards Large-scale Real-world Dataset for Shadow Generation](https://mlsanity.com/paper/2308.09972/) (2023)
- [BOOTPLACE: Bootstrapped Object Placement with Detection Transformers](https://mlsanity.com/paper/2503.21991/) (2025)

## Abstract (arXiv)

Realistic shadow generation is crucial for achieving seamless image compositing, yet existing methods primarily focus on single-object insertion and often fail to generalize when multiple foreground objects are composited into a background scene. In practice, however, modern compositing pipelines and real-world applications often insert multiple objects simultaneously, necessitating shadows that are jointly consistent in terms of geometry, attachment, and location. In this paper, we address the under-explored problem of multi-object shadow generation, aiming to synthesize physically plausible shadows for multiple inserted objects. Our approach exploits the multimodal capabilities of a pre-trained text-to-image diffusion model. An image pathway injects dense, multi-scale features to provide fine-grained spatial guidance, while a text-based pathway encodes per-object shadow bounding boxes as learned positional tokens and fuses them via cross-attention. An attention-alignment loss further grounds these tokens to their corresponding shadow regions. To support this task, we augment the DESOBAv2 dataset by constructing composite scenes with multiple inserted objects and automatically derive prompts combining object category and shadow positioning information. Experimental results demonstrate that our method achieves state-of-the-art performance in both single and multi-object shadow generation settings.