用扩散模型实现高质量零样本材质迁移，可控且自然融合。
MaterialFusion: High-Quality, Zero-Shot, and Controllable Material Transfer with Diffusion Models
- 基于扩散模型实现零样本材质迁移，可调节应用强度。
- 在真实场景数据集上显著提升材质保真度与背景一致性。
- 适合虚拟设计、增强现实等需精细材质控制的场景。
图像中物体材质的操控在增强现实、虚拟原型设计和数字内容创作中至关重要。我们提出 MaterialFusion，一种新型高质材质迁移框架，支持用户调节材质应用程度，实现新材质属性与原物体特征间的最佳平衡。该方法通过保持背景一致性和减少边界伪影，实现物体与场景的无缝融合。为全面评估，我们构建了真实世界材质迁移数据集，并进行了复杂的对比分析。综合定量评估与用户研究显示，MaterialFusion 在质量、用户控制力和背景保留方面显著优于现有方法。代码已公开于 https://github.com/ControlGenAI/MaterialFusion。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。