Online Illumination Learning for Interactive Global Illumination in Augmented Reality, Computer Graphics Lab. @ GIST

Online Illumination Learning for Interactive Global Illumination in Augmented Reality

Wonjun Lee , Piljoong Jeong , Hajin Choi , Jinwoo Kim , Bochang Moon

GIST

IEEE Access

Online Illumination Learning for Interactive Global Illumination in Augmented Reality

Our technique produces interactive AR rendering results using a global illumination technique that simulates light interreflections between real and virtual objects using the scene illumination estimated by our online learning. The example results are generated using a small number of samples per pixel (spp). We use the Disney BSDF for glossy materials of David and Buddha models (in the left and right figures), a mirror material for Lucy and Sphere models (in the middle and right figures), and a diffuse material for the Bunny (in the right figure).

Abstract

Augmenting virtual objects into a real scene requires estimating the scene illumination so that the augmented objects can become visually coherent with real objects. We propose an online technique that learns the illumination from image sequences captured by a hand-held device. We approximate the illumination with multiple linear models, and the coefficients and bandwidth parameters of the models are updated progressively in a data-driven way. Our online learning enables us to seamlessly integrate virtual objects into a real scene by rendering the objects with the estimated lights. We demonstrate that our framework can provide a high-quality global illumination result in augmented reality at interactive rates.