Fast Spatially-Varying Indoor Lighting Estimation
This enables realistic augmented reality applications by allowing virtual objects to be relit in real-time at any position in indoor scenes.
The paper tackles real-time estimation of spatially-varying indoor lighting from a single RGB image, achieving results with lower errors and user preference over state-of-the-art methods in under 20ms on a laptop GPU.
We propose a real-time method to estimate spatiallyvarying 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.