Information
- Publication Type: Conference Paper
- Workgroup(s)/Project(s):
- Date: 2025
- ISBN: 978-989-758-728-3
- Publisher: SciTePress
- Location: Porto
- Lecturer: Annalena Ulschmid
- Event: IVAPP 2025 - Part of VISIGRAPP, the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications.
- DOI: 10.5220/0013193900003912
- Booktitle: Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - GRAPP
- Pages: 14
- Volume: 1
- Conference date: 26. February 2025 – 28. March 2025
- Pages: 113 – 126
- Keywords: Lighting Design, Lighting Style Ttransfer, Texture Synthesis, Lighting Optimization
Abstract
Lighting is a key component in how scenes are perceived. However, many interior lighting situations are currently either handcrafted by expert designers, or simply consist of basic regular arrangements of luminaires, such as to reach uniform lighting at a predefined brightness. Our method aims to bring more interesting lighting configurations to various scenes in a semi-automatic manner designed for fast prototyping by non-expert users. Starting from a single photograph of a lighting configuration, we allow users to quickly copy and adapt a lighting style to any 3D scene. Combining image analysis, texture synthesis, and light parameter optimization, we produce a lighting design for the target 3D scene matching the input image. We validate via a user study that our results successfully transfer the desired lighting style more accurately and realistically than state-of-the-art generic style transfer methods. Furthermore, we investigate the behaviour of our method under potential altern ative choices in an ablation study.Additional Files and Images
No additional files or images.
Weblinks
BibTeX
@inproceedings{ecormier-nocca-2025-sls, title = "Single-Exemplar Lighting Style Transfer via Emissive Texture Synthesis and Optimization", author = "Pierre Ecormier-Nocca and Lukas Lipp and Annalena Ulschmid and David Hahn and Michael Wimmer", year = "2025", abstract = "Lighting is a key component in how scenes are perceived. However, many interior lighting situations are currently either handcrafted by expert designers, or simply consist of basic regular arrangements of luminaires, such as to reach uniform lighting at a predefined brightness. Our method aims to bring more interesting lighting configurations to various scenes in a semi-automatic manner designed for fast prototyping by non-expert users. Starting from a single photograph of a lighting configuration, we allow users to quickly copy and adapt a lighting style to any 3D scene. Combining image analysis, texture synthesis, and light parameter optimization, we produce a lighting design for the target 3D scene matching the input image. We validate via a user study that our results successfully transfer the desired lighting style more accurately and realistically than state-of-the-art generic style transfer methods. Furthermore, we investigate the behaviour of our method under potential altern ative choices in an ablation study.", isbn = "978-989-758-728-3", publisher = "SciTePress", location = "Porto", event = "IVAPP 2025 - Part of VISIGRAPP, the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications.", doi = "10.5220/0013193900003912", booktitle = "Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - GRAPP", pages = "14", volume = "1", pages = "113--126", keywords = "Lighting Design, Lighting Style Ttransfer, Texture Synthesis, Lighting Optimization", URL = "https://www.cg.tuwien.ac.at/research/publications/2025/ecormier-nocca-2025-sls/", }