Accidental Light Probes
This addresses the challenge of lighting estimation in everyday images where traditional light probes are unavailable, offering a practical solution for computer vision applications.
The paper tackles the problem of recovering scene lighting from a single image by using accidental light probes (ALPs), such as shiny objects like Coke cans, and proposes a physically-based approach to model and invert their appearance for lighting estimation, achieving high-fidelity results.
Recovering lighting in a scene from a single image is a fundamental problem in computer vision. While a mirror ball light probe can capture omnidirectional lighting, light probes are generally unavailable in everyday images. In this work, we study recovering lighting from accidental light probes (ALPs) -- common, shiny objects like Coke cans, which often accidentally appear in daily scenes. We propose a physically-based approach to model ALPs and estimate lighting from their appearances in single images. The main idea is to model the appearance of ALPs by photogrammetrically principled shading and to invert this process via differentiable rendering to recover incidental illumination. We demonstrate that we can put an ALP into a scene to allow high-fidelity lighting estimation. Our model can also recover lighting for existing images that happen to contain an ALP.