让图像物体可精准涂抹材质层，保留原有细节。
CoatFusion: Controllable Material Coating in Images
- 用扩散模型结合贴图与物理参数控制材质涂层
- 在110K合成数据集上实现逼真可控的材质涂抹
- 适合需要精细材质编辑的视觉设计场景
我们提出材料涂抹这一新图像编辑任务，模拟在物体表面添加一层薄材料，同时保持其粗粒度和细粒度几何结构。该任务不同于现有材料迁移方法，后者常替换物体固有材质并破坏细节。为此，我们构建了包含110,000张3D物体图像的大规模合成数据集DataCoat110K，涵盖多种基于物理的涂层。我们提出CoatFusion架构，通过条件扩散模型，结合2D漫反射贴图与颗粒级的PBR参数（如粗糙度、金属度、透射率及关键厚度参数），实现可控材质涂抹。实验与用户研究显示，CoatFusion生成结果真实且可控，在此任务上显著优于现有材料编辑与迁移方法。
原文摘要 · Abstract (English)
We introduce Material Coating, a novel image editing task that simulates applying a thin material layer onto an object while preserving its underlying coarse and fine geometry. Material coating is fundamentally different from existing "material transfer" methods, which are designed to replace an object's intrinsic material, often overwriting fine details. To address this new task, we construct a large-scale synthetic dataset (110K images) of 3D objects with varied, physically-based coatings, named DataCoat110K. We then propose CoatFusion, a novel architecture that enables this task by conditioning a diffusion model on both a 2D albedo texture and granular, PBR-style parametric controls, including roughness, metalness, transmission, and a key thickness parameter. Experiments and user studies show CoatFusion produces realistic, controllable coatings and significantly outperforms existing material editing and transfer methods on this new task.
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。