The Clutterpalette: An Interactive Tool for Detailing Indoor Scenes

Lap-Fai Yu¹	Sai-Kit Yeung²	Demetri Terzopoulos³
¹University of Massachusetts Boston	²Singapore University of Technology and Design	³University of California, Los Angeles

Abstract We introduce the Clutterpalette, an interactive tool for detailing indoor scenes with small-scale items. When the user points to a location in the scene, the Clutterpalette suggests detail items for that location. In order to present appropriate suggestions, the Clutterpalette is trained on a dataset of images of real-world scenes, annotated with support relations. Our experiments demonstrate that the adaptive suggestions presented by the Clutterpalette increase modeling speed and enhance the realism of indoor scenes.

Keywords: interactive 3D modeling, scene modeling, scene understanding, indoor scenes, modeling tools, suggestive user interfaces

Publications:

The Clutterpalette: An Interactive Tool for Detailing Indoor Scenes
Lap-Fai Yu, Sai-Kit Yeung, Demetri Terzopoulos
IEEE Transactions on Visualization and Computer Graphics (TVCG), 2014
Paper (Low Res), Paper (High Res), Video

BibTex:

@article{clutter,
    author = {Lap-Fai Yu and Sai Kit Yeung and Demetri Terzopoulos},
    title = {The Clutterpalette: An Interactive Tool for Detailing Indoor Scenes},
    journal = {IEEE Transactions on Visualization and Computer Graphics},
    year = {2015}
}

Acknowledgements:

The authors would like to thank Vladlen Koltun for discussing ideas, Ariel Shamir and Qiming Hou for their valuable comments, Yibiao Zhao for helping with the evaluation, and Michael S. Brown for narrating the demonstration video. This research was supported in part by Singapore University of Technology and Design (SUTD) StartUp Grant ISTD 2011 016, by SUTD-MIT International Design Center Grant IDG31300106, Singapore MOE Academic Research Fund MOE2013-T2-1-159, National Research Foundation, Prime Minister’s Office, Singapore, under its IDM Futures Funding Initiative, administered by the Interactive and Digital Media Programme Office, and by University of Massachusetts Boston StartUp Grant P20150000029280.