Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2508.14930 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916910595047424 |
|---|---|
| author | Zhao, Hanwen Akers, John Elmieh, Baback Kemelmacher-Shlizerman, Ira |
| author_facet | Zhao, Hanwen Akers, John Elmieh, Baback Kemelmacher-Shlizerman, Ira |
| contents | Mixed Reality scene relighting, where virtual changes to lighting conditions realistically interact with physical objects, producing authentic illumination and shadows, can be used in a variety of applications. One such application in real estate could be visualizing a room at different times of day and placing virtual light fixtures. Existing deep learning-based relighting techniques typically exceed the real-time performance capabilities of current MR devices. On the other hand, scene understanding methods, such as on-device scene reconstruction, often yield inaccurate results due to scanning limitations, in turn affecting relighting quality. Finally, simpler 2D image filter-based approaches cannot represent complex geometry and shadows. We introduce a novel method to integrate image segmentation, with lighting propagation via anisotropic diffusion on top of basic scene understanding, and the computational simplicity of filter-based techniques. Our approach corrects on-device scanning inaccuracies, delivering visually appealing and accurate relighting effects in real-time on edge devices, achieving speeds as high as 100 fps. We show a direct comparison between our method and the industry standard, and present a practical demonstration of our method in the aforementioned real estate example. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_14930 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Hybrelighter: Combining Deep Anisotropic Diffusion and Scene Reconstruction for On-device Real-time Relighting in Mixed Reality Zhao, Hanwen Akers, John Elmieh, Baback Kemelmacher-Shlizerman, Ira Graphics Mixed Reality scene relighting, where virtual changes to lighting conditions realistically interact with physical objects, producing authentic illumination and shadows, can be used in a variety of applications. One such application in real estate could be visualizing a room at different times of day and placing virtual light fixtures. Existing deep learning-based relighting techniques typically exceed the real-time performance capabilities of current MR devices. On the other hand, scene understanding methods, such as on-device scene reconstruction, often yield inaccurate results due to scanning limitations, in turn affecting relighting quality. Finally, simpler 2D image filter-based approaches cannot represent complex geometry and shadows. We introduce a novel method to integrate image segmentation, with lighting propagation via anisotropic diffusion on top of basic scene understanding, and the computational simplicity of filter-based techniques. Our approach corrects on-device scanning inaccuracies, delivering visually appealing and accurate relighting effects in real-time on edge devices, achieving speeds as high as 100 fps. We show a direct comparison between our method and the industry standard, and present a practical demonstration of our method in the aforementioned real estate example. |
| title | Hybrelighter: Combining Deep Anisotropic Diffusion and Scene Reconstruction for On-device Real-time Relighting in Mixed Reality |
| topic | Graphics |
| url | https://arxiv.org/abs/2508.14930 |