ControlCom: Controllable Image Composition using Diffusion Model
This work solves the image composition problem for computer vision and graphics applications, offering incremental improvements in controllability and fidelity.
The paper tackles the problem of synthesizing realistic composite images from foreground and background pairs by addressing lack of controllability and poor identity preservation in existing methods, proposing a unified diffusion model that achieves more faithful and controllable results than prior approaches.
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.