Affordance-Aware Object Insertion via Mask-Aware Dual Diffusion
This work addresses the challenge of seamlessly inserting objects into scenes for image editing applications, representing an incremental improvement with a novel method for a known bottleneck.
The paper tackles the problem of affordance-aware object insertion in image composition by proposing the Mask-Aware Dual Diffusion (MADD) model, which outperforms state-of-the-art methods and shows strong generalization on in-the-wild images.
As a common image editing operation, image composition involves integrating foreground objects into background scenes. In this paper, we expand the application of the concept of Affordance from human-centered image composition tasks to a more general object-scene composition framework, addressing the complex interplay between foreground objects and background scenes. Following the principle of Affordance, we define the affordance-aware object insertion task, which aims to seamlessly insert any object into any scene with various position prompts. To address the limited data issue and incorporate this task, we constructed the SAM-FB dataset, which contains over 3 million examples across more than 3,000 object categories. Furthermore, we propose the Mask-Aware Dual Diffusion (MADD) model, which utilizes a dual-stream architecture to simultaneously denoise the RGB image and the insertion mask. By explicitly modeling the insertion mask in the diffusion process, MADD effectively facilitates the notion of affordance. Extensive experimental results show that our method outperforms the state-of-the-art methods and exhibits strong generalization performance on in-the-wild images. Please refer to our code on https://github.com/KaKituken/affordance-aware-any.