We propose a method to control material attributes of objects like roughness, metallic, albedo, and transparency in real images. Our method capitalizes on the generative prior of text-to-image models known for photorealism, employing a scalar value and instructions to alter low-level material properties. Addressing the lack of datasets with controlled material attributes, we generated an object-centric synthetic dataset with physically-based materials. Fine-tuning a modified pre-trained text-to-image model on this synthetic dataset enables us to edit material properties in real-world images while preserving all other attributes. We show the potential application of our model to material edited NeRFs.
Cite
@article{arxiv.2312.02970,
title = {Alchemist: Parametric Control of Material Properties with Diffusion Models},
author = {Prafull Sharma and Varun Jampani and Yuanzhen Li and Xuhui Jia and Dmitry Lagun and Fredo Durand and William T. Freeman and Mark Matthews},
journal= {arXiv preprint arXiv:2312.02970},
year = {2023}
}