MaterialFusion: High-Quality, Zero-Shot, and Controllable Material Transfer with Diffusion Models
This addresses the need for better material manipulation in digital content creation, though it appears incremental as it builds on diffusion models.
The paper tackles the problem of manipulating material appearance in images for applications like augmented reality, introducing MaterialFusion, a framework that achieves high-quality, controllable material transfer with improved quality, user control, and background preservation compared to existing methods.
Manipulating the material appearance of objects in images is critical for applications like augmented reality, virtual prototyping, and digital content creation. We present MaterialFusion, a novel framework for high-quality material transfer that allows users to adjust the degree of material application, achieving an optimal balance between new material properties and the object's original features. MaterialFusion seamlessly integrates the modified object into the scene by maintaining background consistency and mitigating boundary artifacts. To thoroughly evaluate our approach, we have compiled a dataset of real-world material transfer examples and conducted complex comparative analyses. Through comprehensive quantitative evaluations and user studies, we demonstrate that MaterialFusion significantly outperforms existing methods in terms of quality, user control, and background preservation. Code is available at https://github.com/ControlGenAI/MaterialFusion.