DeepLight: Learning Illumination for Unconstrained Mobile Mixed Reality
This addresses the challenge of realistic virtual object integration in mobile mixed reality for users, though it is incremental as it builds on existing learning-based approaches.
The paper tackles the problem of inferring high dynamic range, omnidirectional illumination from a single low dynamic range mobile phone image to enable realistic mixed reality rendering, achieving interactive frame rates on mobile devices and improving realism compared to state-of-the-art methods for indoor and outdoor scenes.
We present a learning-based method to infer plausible high dynamic range (HDR), omnidirectional illumination given an unconstrained, low dynamic range (LDR) image from a mobile phone camera with a limited field of view (FOV). For training data, we collect videos of various reflective spheres placed within the camera's FOV, leaving most of the background unoccluded, leveraging that materials with diverse reflectance functions reveal different lighting cues in a single exposure. We train a deep neural network to regress from the LDR background image to HDR lighting by matching the LDR ground truth sphere images to those rendered with the predicted illumination using image-based relighting, which is differentiable. Our inference runs at interactive frame rates on a mobile device, enabling realistic rendering of virtual objects into real scenes for mobile mixed reality. Training on automatically exposed and white-balanced videos, we improve the realism of rendered objects compared to the state-of-the art methods for both indoor and outdoor scenes.