GLTScene: Global-to-Local Transformers for Indoor Scene Synthesis with General Room Boundaries
No Thumbnail Available
Date
2024
Journal Title
Journal ISSN
Volume Title
Publisher
The Eurographics Association and John Wiley & Sons Ltd.
Abstract
We present GLTScene, a novel data-driven method for high-quality furniture layout synthesis with general room boundaries as conditions. This task is challenging since the existing indoor scene datasets do not cover the variety of general room boundaries. We incorporate the interior design principles with learning techniques and adopt a global-to-local strategy for this task. Globally, we learn the placement of furniture objects from the datasets without considering their alignment. Locally, we learn the alignment of furniture objects relative to their nearest walls, according to the alignment principle in interior design. The global placement and local alignment of furniture objects are achieved by two transformers respectively. We compare our method with several baselines in the task of furniture layout synthesis with general room boundaries as conditions. Our method outperforms these baselines both quantitatively and qualitatively. We also demonstrate that our method can achieve other conditional layout synthesis tasks, including object-level conditional generation and attribute-level conditional generation. The code is publicly available at https://github.com/WWalter-Lee/GLTScene.
Description
@article{10.1111:cgf.15236,
journal = {Computer Graphics Forum},
title = {{GLTScene: Global-to-Local Transformers for Indoor Scene Synthesis with General Room Boundaries}},
author = {Li, Yijie and Xu, Pengfei and Ren, Junquan and Shao, Zefan and Huang, Hui},
year = {2024},
publisher = {The Eurographics Association and John Wiley & Sons Ltd.},
ISSN = {1467-8659},
DOI = {10.1111/cgf.15236}
}