max planck institut informatik
The material found on 3D objects and their parts in our everyday surroundings is highly correlated with the geometric shape of the parts and their relation to other parts of the same object. This work proposes to model this context-dependent correlation by learning it from a database containing several hundreds of objects and their materials. Given a part-based 3D object without materials, the learned model can be used to fully automatically assign plausible material parameters, including diffuse color, specularity, gloss, and transparency. Further, we propose a user interface that provides material suggestions. This user-interface can be used, for example, to refine the automatic suggestion. Once a refinement has been made, the model incorporates this information, and the automatic assignment is incrementally improved. Results are given for objects with different numbers of parts and with different topological complexity. A user study validates that our method significantly simplifies and accelerates the material assignment task compared to other approaches.
| Paper (Adobe Acrobat PDF, 10.6 MB). | |
| Video (Windows AVI, Xvid, 68.9 MB). | |
| Supplemental results (Adobe Acrobat PDF, 5.85 MB). | |
| User study instructions and results (Adobe Acrobat PDF, 1.79 MB). | |
| Siggraph Asia 2012 talk slides (Microsoft Power Point 2010, 40.0 MB). |
Arjun Jain, Thorsten Thormählen, Tobias Ritschel, Hans-Peter Seidel
Material Memex: Automatic Material Suggestions for 3D Objects
ACM Trans. Graph. 31 (5) (Proc. SIGGRAPH Asia 2012, Singapore, 28 Nov – 1 Dec 2012).
@article{Jain:2012:MaterialMemex,
author = {Arjun Jain and Thorsten Thorm\"ahlen and Tobias Ritschel and Hans-Peter Seidel},
title = {Material Memex: Automatic Material Suggestions for 3D Objects},
journal = {ACM Trans. Graph. (Proc. SIGGRAPH Asia 2012)},
year = {2012},
volume = {31},
number = {5}
}
This work has been partially funded by the Max Planck Center for Visual Computing and Communication (BMBF-FKZ01IMC01).
We thank