ZeST: Zero-Shot Material Transfer from a Single Image

TL;DR

ZeST introduces a zero-shot method for transferring materials onto objects in images using diffusion models, without any training, achieving photorealistic results and enabling multiple edits under varying lighting conditions.

Contribution

ZeST is the first zero-shot approach that transfers materials in images using diffusion models without training, leveraging implicit material representations from exemplars.

Findings

Produces photorealistic material transfer results.

Works effectively on real and synthetic images.

Enables multiple edits and robust material assignment.

Abstract

We propose ZeST, a method for zero-shot material transfer to an object in the input image given a material exemplar image. ZeST 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 ZeST outputs photorealistic images with transferred materials. We also show the application of ZeST to perform multiple edits and robust material assignment under different illuminations. Project Page: https://ttchengab.github.io/zest