Abstract: Assigning textures and materials within 3D scenes is a tedious and labor-intensive task. In this paper, we present Magic Decorator, a system that automatically generates material suggestions for 3D indoor scenes. To achieve this goal, we introduce local material rules, which describe typical material patterns for a small group of objects or parts, and global aesthetic rules, which account for the harmony among the entire set of colors in a specific scene. Both rules are obtained from collections of indoor scene images. We cast the problem of material suggestion as a combinatorial optimization considering both local material and global aesthetic rules. We have tested our system on various complex indoor scenes. A user study indicates that our system can automatically and efficiently produce a series of visually plausible material suggestions which are comparable to those produced by artists.

Paper: [PDF 22M].
Supplemental Document: [PDF 45M].
Video: [MP4 45M].
Presentation: [PPTX 85M].


Database: [RAR 270K].
Image Labeling Tool V2: [RAR 11M].

Bibtex:

@article{Chen:2015:MDA:2816795.2818096, author = {Chen, Kang and Xu, Kun and Yu, Yizhou and Wang, Tian-Yi and Hu, Shi-Min}, title = {Magic Decorator: Automatic Material Suggestion for Indoor Digital Scenes}, journal = {ACM Trans. Graph.}, issue_date = {November 2015}, volume = {34}, number = {6}, month = oct, year = {2015}, issn = {0730-0301}, pages = {232:1--232:11}, articleno = {232}, numpages = {11}, url = {http://doi.acm.org/10.1145/2816795.2818096}, doi = {10.1145/2816795.2818096}, acmid = {2818096}, publisher = {ACM}, address = {New York, NY, USA}, keywords = {computer-aided aesthetic design, data-driven content creation, indoor scene, material suggestion}, }