MatFuse：基于扩散模型的可控材质生成
MatFuse: Controllable Material Generation with Diffusion Models
AI总结：
本文提出MatFuse，一种利用扩散模型生成和编辑3D材质的统一方法，通过集成多种条件源实现细粒度控制，并支持基于解耦潜在表示的贴图级编辑。
摘要：
在计算机图形学中创建高质量材质是一项极具挑战且耗时的任务，需要深厚的专业知识。为简化这一过程，我们引入了MatFuse，这是一种统一的方法，利用扩散模型的生成能力来创建和编辑3D材质。我们的方法集成了多种条件来源，包括调色板、草图、文本和图片，增强了创作可能性，并赋予了对材质合成的细粒度控制。此外，MatFuse通过潜在操作实现了贴图级别的材质编辑功能，该操作借助一个多编码器压缩模型，为每个贴图学习一种解耦的潜在表示。我们在多种条件设置下展示了MatFuse的有效性，并探索了材质编辑的潜力。最后，我们通过CLIP-IQA和FID分数定量评估了生成材质的质量，并通过用户研究进行了定性评估。用于训练MatFuse的源代码和补充材料已在 https://gvecchio.com/matfuse 公开。
英文摘要：
Creating high-quality materials in computer graphics is a challenging and time-consuming task, which requires great expertise. To simplify this process, we introduce MatFuse, a unified approach that harnesses the generative power of diffusion models for creation and editing of 3D materials. Our method integrates multiple sources of conditioning, including color palettes, sketches, text, and pictures, enhancing creative possibilities and granting fine-grained control over material synthesis. Additionally, MatFuse enables map-level material editing capabilities through latent manipulation by means of a multi-encoder compression model which learns a disentangled latent representation for each map. We demonstrate the effectiveness of MatFuse under multiple conditioning settings and explore the potential of material editing. Finally, we assess the quality of the generated materials both quantitatively in terms of CLIP-IQA and FID scores and qualitatively by conducting a user study. Source code for training MatFuse and supplemental materials are publicly available at https://gvecchio.com/matfuse.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
