Single-image SVBRDF capture with a rendering-aware deep network

© 2018 Copyright held by the owner/author(s). Texture, highlights, and shading are some of many visual cues that allow humans to perceive material appearance in single pictures. Yet, recovering spatially-varying bi-directional reflectance distribution functions (SVBRDFs) from a single image based on...

ver descrição completa

Detalhes bibliográficos
Principais autores: Deschaintre, Valentin, Aittala, Miika, Durand, Fredo, Drettakis, George, Bousseau, Adrien
Outros Autores: Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Formato: Artigo
Idioma:English
Publicado em: Association for Computing Machinery (ACM) 2021
Acesso em linha:https://hdl.handle.net/1721.1/136366