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

TL;DR

MultiShadow introduces a diffusion model-based approach for generating realistic, multi-object shadows in image compositing, addressing the challenge of joint consistency among multiple inserted objects.

Contribution

It presents a novel diffusion model framework that jointly generates shadows for multiple objects, incorporating spatial guidance and learned positional tokens for improved realism.

Findings

Achieves state-of-the-art results in multi-object shadow generation

Successfully generalizes from single to multiple object scenarios

Enhances dataset with composite scenes for training and evaluation

Abstract

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.