CoatFusion: Controllable Material Coating in Images

TL;DR

This paper introduces a new image editing task called Material Coating, which applies a controllable, realistic thin material layer onto objects in images, preserving underlying geometry and details.

Contribution

The paper presents a novel task, a large synthetic dataset, and a diffusion-based model, CoatFusion, for controllable material coating in images, outperforming existing methods.

Findings

CoatFusion produces realistic, controllable coatings.

It significantly outperforms existing material editing methods.

User studies validate the quality and controllability of results.

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.