Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2512.02143 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914177230045184 |
|---|---|
| author | Levy, Sagie Aharoni, Elad Levy, Matan Shamir, Ariel Lischinski, Dani |
| author_facet | Levy, Sagie Aharoni, Elad Levy, Matan Shamir, Ariel Lischinski, Dani |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_02143 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | CoatFusion: Controllable Material Coating in Images Levy, Sagie Aharoni, Elad Levy, Matan Shamir, Ariel Lischinski, Dani Graphics Computer Vision and Pattern Recognition Machine Learning 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. |
| title | CoatFusion: Controllable Material Coating in Images |
| topic | Graphics Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2512.02143 |