IllumiNet: Transferring Illumination from Planar Surfaces to Virtual Objects in Augmented Reality
This addresses the challenge of achieving realistic augmented reality experiences for users by providing a robust illumination estimation method.
The paper tackles the problem of realistic illumination for virtual objects in augmented reality by transferring illumination features from planar surfaces to geometries, outperforming state-of-the-art methods in both indoor and outdoor environments.
This paper presents an illumination estimation method for virtual objects in real environment by learning. While previous works tackled this problem by reconstructing high dynamic range (HDR) environment maps or the corresponding spherical harmonics, we do not seek to recover the lighting environment of the entire scene. Given a single RGB image, our method directly infers the relit virtual object by transferring the illumination features extracted from planar surfaces in the scene to the desired geometries. Compared to previous works, our approach is more robust as it works in both indoor and outdoor environments with spatially-varying illumination. Experiments and evaluation results show that our approach outperforms the state-of-the-art quantitatively and qualitatively, achieving realistic augmented experience.