Abstract | ||
---|---|---|
We propose a real-time method to estimate spatially-varying indoor lighting from a single RGB image. Given an image and a 2D location in that image, our CNN estimates a 5th order spherical harmonic representation of the lighting at the given location in less than 20ms on a laptop mobile graphics card. While existing approaches estimate a single, global lighting representation or require depth as input, our method reasons about local lighting without requiring any geometry information. We demonstrate, through quantitative experiments including a user study, that our results achieve lower lighting estimation errors and are preferred by users over the state-of-the-art. Our approach can be used directly for augmented reality applications,where a virtual object is relit realistically at any position in the scene in real-time. |
Year | DOI | Venue |
---|---|---|
2019 | 10.1109/CVPR.2019.00707 | 2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019) |
DocType | Volume | ISSN |
Conference | abs/1906.03799 | 1063-6919 |
Citations | PageRank | References |
6 | 0.40 | 0 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Mathieu Garon | 1 | 18 | 1.28 |
Kalyan Sunkavalli | 2 | 500 | 31.75 |
Sunil Hadap | 3 | 27 | 2.00 |
Nathan Carr | 4 | 232 | 17.24 |
Jean-françois Lalonde | 5 | 590 | 37.69 |