ZeST: Zero-Shot Material Transfer from a Single Image
Abstract
We propose , a method for zero-shot material transfer to an object in the input image given a material exemplar image. leverages existing diffusion adapters to extract implicit material representation from the exemplar image. This representation is used to transfer the material using pre-trained inpainting diffusion model on the object in the input image using depth estimates as geometry cue and grayscale object shading as illumination cues. The method works on real images without any training resulting a zero-shot approach. Both qualitative and quantitative results on real and synthetic datasets demonstrate that outputs photorealistic images with transferred materials. We also show the application of to perform multiple edits and robust material assignment under different illuminations. Project Page: https://ttchengab.github.io/zest
Cite
Text
Cheng et al. "ZeST: Zero-Shot Material Transfer from a Single Image." Proceedings of the European Conference on Computer Vision (ECCV), 2024. doi:10.1007/978-3-031-73232-4_21Markdown
[Cheng et al. "ZeST: Zero-Shot Material Transfer from a Single Image." Proceedings of the European Conference on Computer Vision (ECCV), 2024.](https://mlanthology.org/eccv/2024/cheng2024eccv-zest/) doi:10.1007/978-3-031-73232-4_21BibTeX
@inproceedings{cheng2024eccv-zest,
title = {{ZeST: Zero-Shot Material Transfer from a Single Image}},
author = {Cheng, Ta-Ying and Sharma, Prafull and Markham, Andrew and Trigoni, Niki and Jampani, Varun},
booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
year = {2024},
doi = {10.1007/978-3-031-73232-4_21},
url = {https://mlanthology.org/eccv/2024/cheng2024eccv-zest/}
}