Abstract
Conventionally, interior lighting design is technically complex yet challenging and requires professional knowledge and aesthetic disciplines of designers. This article presents a new digital lighting design framework for virtual interior scenes, which allows novice users to automatically obtain lighting layouts and interior rendering images with visually pleasing lighting effects. The proposed framework utilizes neural networks to retrieve and learn underlying design guidelines and the principles beneath the existing lighting designs, e.g., a newly constructed dataset of 6k 3D interior scenes from professional designers with dense annotations of lights. With a 3D furniture-populated indoor scene as the input, the framework takes two stages to perform lighting design: (1) lights are iteratively placed in the room; (2) the colors and intensities of the lights are optimized by an adversarial scheme, resulting in lighting designs with aesthetic lighting effects. Quantitative and qualitative experiments show that the proposed framework effectively learns the guidelines and principles and generates lighting designs that are preferred over the rule-based baseline and comparable to those of professional human designers.
Visual Results
Free-view Walk-through
Acknowledgements
We would like to thank all reviewers for their insightful comments. We also thank Jialin Huang, Bing Xu for preparing the dataset and helpful discussions, Jacob Si for preparing the video, Yunjin Zhang for proofreading the article, and all participants in our perceptual studies.
Citation
@article{10.1145/3582001,
author = {Ren, Haocheng and Fan, Hangming and Wang, Rui and Huo, Yuchi and Tang, Rui and Wang, Lei and Bao, Hujun},
title = {Data-Driven Digital Lighting Design for Residential Indoor Spaces},
year = {2023},
issue_date = {June 2023},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
volume = {42},
number = {3},
issn = {0730-0301},
url = {https://doi.org/10.1145/3582001},
journal = {ACM Trans. Graph.},
doi = {10.1145/3582001},
month = {mar},
articleno = {28},
numpages = {18},
keywords = {Lighting design, neural network, interior design, deep learning, data-driven approach}}