MaterialFusion: High-Quality, Zero-Shot, and Controllable Material Transfer with Diffusion Models

TL;DR

MaterialFusion is a new diffusion-based framework that enables high-quality, controllable, zero-shot material transfer in images, maintaining scene consistency and allowing user adjustments for optimal results.

Contribution

It introduces a novel diffusion model approach for material transfer that offers improved quality, controllability, and background preservation compared to existing methods.

Findings

Outperforms existing methods in quality and control

Achieves seamless integration with minimal boundary artifacts

Validated through extensive quantitative and user studies

Abstract

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.