跳到正文
返回论文列表
cs.GR提交于 已译

CoatFusion: 图像中的可控材料涂层

CoatFusion: Controllable Material Coating in Images

Sagie Levy · Elad Aharoni · Matan Levy · Ariel Shamir · Dani Lischinski

中文摘要

引入材料涂层(Material Coating)这一新型图像编辑任务,旨在模拟在物体表面施加薄层材料,同时保留其底层粗糙与精细几何结构。该任务与旨在替换物体固有材料并常覆盖细节的现有“材料迁移”方法存在本质差异。为此,构建了包含 110K 张图像的大规模合成数据集 DataCoat110K,涵盖具有不同基于物理(PBR)涂层的 3D 物体。提出 CoatFusion 架构,通过以 2D 反照率纹理及粗糙度、金属度、透射率、厚度等细粒度 PBR 参数化控制为条件,驱动扩散模型实现该任务。实验与用户研究表明,CoatFusion 能生成真实且可控的涂层效果,并在此新任务上显著优于现有的材料编辑与迁移方法。

关键要点

  1. 01定义材料涂层任务,区别于替换固有材料的迁移方法,强调保留底层几何细节。
  2. 02构建 DataCoat110K 数据集,包含 110K 张具有不同 PBR 物理涂层的 3D 物体图像。
  3. 03提出 CoatFusion 架构,利用 2D 反照率纹理及粗糙度、金属度、厚度等 PBR 参数控制扩散模型。
  4. 04实验与用户研究证实,CoatFusion 在生成真实可控涂层方面显著优于现有材料编辑与迁移方法。

解读

尚无解读。

原始英文摘要

arXiv:2512.02143v2 Announce Type: replace-cross Abstract: 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.

同方向论文 · cs.GR

查看全部 →