We present a novel U-Attention vision Transformer for universal texture synthesis.
We learn a latent space for easy capture, consistent interpolation, and efficient reproduction of visual material appearance.
Our solution is extremely simple: we fine-tune a deep appearance-capture network on the provided exemplars, such that it learns to extract similar SVBRDF values from the target image.
Empowered by deep learning, recent methods for material capture can estimate a spatially-varying reflectance from a single photograph.
Texture, highlights, and shading are some of many visual cues that allow humans to perceive material appearance in single pictures.