ZeST: Zero-Shot Material Transfer from a Single Image
This enables zero-shot material editing for applications in computer graphics and vision, though it is incremental as it builds on existing diffusion adapters and models.
The authors tackled the problem of transferring materials from a single exemplar image to an object in an input image without training, achieving photorealistic results as demonstrated on real and synthetic datasets.
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