ControlCom: Controllable Image Composition using Diffusion Model

TL;DR

ControlCom introduces a unified diffusion-based approach for controllable image composition, enabling tasks like blending, harmonization, view synthesis, and generation with improved foreground fidelity and user control.

Contribution

It unifies four image composition tasks into one diffusion model and proposes a self-supervised training framework with a local enhancement module for better foreground details.

Findings

Outperforms existing methods in faithfulness and controllability

Demonstrates effectiveness on benchmark and real-world data

Enhances foreground fidelity in composite images

Abstract

Image composition targets at synthesizing a realistic composite image from a pair of foreground and background images. Recently, generative composition methods are built on large pretrained diffusion models to generate composite images, considering their great potential in image generation. However, they suffer from lack of controllability on foreground attributes and poor preservation of foreground identity. To address these challenges, we propose a controllable image composition method that unifies four tasks in one diffusion model: image blending, image harmonization, view synthesis, and generative composition. Meanwhile, we design a self-supervised training framework coupled with a tailored pipeline of training data preparation. Moreover, we propose a local enhancement module to enhance the foreground details in the diffusion model, improving the foreground fidelity of composite images. The proposed method is evaluated on both public benchmark and real-world data, which demonstrates that our method can generate more faithful and controllable composite images than existing approaches. The code and model will be available at https://github.com/bcmi/ControlCom-Image-Composition.