Guided Fine‐Tuning for Large‐Scale Material Transfer. (20th July 2020)

• Record Type: Journal Article
• Authors: Deschaintre, Valentin; Drettakis, George; Bousseau, Adrien
• Is Part Of: Computer graphics forum. Volume 39:Number 4(2020)
• Page Start: 91
• Page End: 105
• Publication Date: 2020-07-20
• Subjects: CCS Concepts -- Computing methodologies → Reflectance modeling -- Image processing; material transfer -- material capture -- appearance capture -- SVBRDF -- deep learning -- fine tuning; Computer graphics -- Periodicals; 006.605
• DOI: 10.1111/cgf.14056
• Languages: English
• ISSNs: 0167-7055

Abstract

Abstract: We present a method to transfer the appearance of one or a few exemplar SVBRDFs to a target image representing similar materials. 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. We introduce two novel material capture and design workflows that demonstrate the strength of this simple approach. Our first workflow allows to produce plausible SVBRDFs of large‐scale objects from only a few pictures. Specifically, users only need take a single picture of a large surface and a few close‐up flash pictures of some of its details. We use existing methods to extract SVBRDF parameters from the close‐ups, and our method to transfer these parameters to the entire surface, enabling the lightweight capture of surfaces several meters wide such as murals, floors and furniture. In our second workflow, we provide a powerful way for users to create large SVBRDFs from internet pictures by transferring the appearance of existing, pre‐designed SVBRDFs. By selecting different exemplars, users can control the materials assigned to the target image, greatly enhancing the creative possibilities offered by deep appearance capture.