Lighting, Reflectance and Geometry Estimation from 360$^{\circ}$ Panoramic Stereo
This addresses the challenge of scene understanding for augmented reality applications, representing an incremental improvement over existing methods.
The paper tackles the problem of estimating high-definition spatially-varying lighting, reflectance, and geometry from 360° stereo images, and the result shows that the method outperforms prior state-of-the-art methods, enabling applications like mirror-objects insertion in augmented reality.
We propose a method for estimating high-definition spatially-varying lighting, reflectance, and geometry of a scene from 360$^{\circ}$ stereo images. Our model takes advantage of the 360$^{\circ}$ input to observe the entire scene with geometric detail, then jointly estimates the scene's properties with physical constraints. We first reconstruct a near-field environment light for predicting the lighting at any 3D location within the scene. Then we present a deep learning model that leverages the stereo information to infer the reflectance and surface normal. Lastly, we incorporate the physical constraints between lighting and geometry to refine the reflectance of the scene. Both quantitative and qualitative experiments show that our method, benefiting from the 360$^{\circ}$ observation of the scene, outperforms prior state-of-the-art methods and enables more augmented reality applications such as mirror-objects insertion.