Alchemist: Parametric Control of Material Properties with Diffusion Models

Abstract

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

Text

Sharma et al. "Alchemist: Parametric Control of Material Properties with Diffusion Models." Conference on Computer Vision and Pattern Recognition, 2024. doi:10.1109/CVPR52733.2024.02278

Markdown

[Sharma et al. "Alchemist: Parametric Control of Material Properties with Diffusion Models." Conference on Computer Vision and Pattern Recognition, 2024.](https://mlanthology.org/cvpr/2024/sharma2024cvpr-alchemist/) doi:10.1109/CVPR52733.2024.02278

BibTeX

@inproceedings{sharma2024cvpr-alchemist,
  title     = {{Alchemist: Parametric Control of Material Properties with Diffusion Models}},
  author    = {Sharma, Prafull and Jampani, Varun and Li, Yuanzhen and Jia, Xuhui and Lagun, Dmitry and Durand, Fredo and Freeman, Bill and Matthews, Mark},
  booktitle = {Conference on Computer Vision and Pattern Recognition},
  year      = {2024},
  pages     = {24130-24141},
  doi       = {10.1109/CVPR52733.2024.02278},
  url       = {https://mlanthology.org/cvpr/2024/sharma2024cvpr-alchemist/}
}