Match: differentiable material graphs for procedural material capture
© 2020 Owner/Author. We present MATch, a method to automatically convert photographs of material samples into production-grade procedural material models. At the core of MATch is a new library DiffMat that provides differentiable building blocks for constructing procedural materials, and automatic t...
Main Authors: | Shi, Liang, Li, Beichen, Hašan, Miloš, Sunkavalli, Kalyan, Boubekeur, Tamy, Mech, Radomir, Matusik, Wojciech |
---|---|
Other Authors: | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory |
Format: | Article |
Language: | English |
Published: |
Association for Computing Machinery (ACM)
2021
|
Online Access: | https://hdl.handle.net/1721.1/134067 |
Similar Items
-
End-to-end Procedural Material Capture with Proxy-Free Mixed-Integer Optimization
by: Li, Beichen, et al.
Published: (2023) -
Multi-scale image harmonization
by: Sunkavalli, Kalyan, et al.
Published: (2021) -
Procedural Metamaterials: A Unified Procedural Graph for Metamaterial Design
by: Makatura, Liane, et al.
Published: (2023) -
Video face replacement
by: Dale, Kevin, et al.
Published: (2012) -
End-to-end learning of 3D phase-only holograms for holographic display
by: Liang Shi, et al.
Published: (2022-08-01)