Real-time Light Estimation and Neural Soft Shadows for AR Indoor Scenarios
This work addresses the challenge of achieving realistic AR integration for mobile applications, though it is incremental as it builds on existing deep learning and neural rendering techniques.
The paper tackles the problem of realistically embedding virtual objects into indoor AR scenes by introducing a pipeline with a light estimator and a neural soft shadow generator, achieving real-time performance with runtimes of 9ms for light estimation and 5ms for neural shadows on an iPhone 11 Pro.
We present a pipeline for realistic embedding of virtual objects into footage of indoor scenes with focus on real-time AR applications. Our pipeline consists of two main components: A light estimator and a neural soft shadow texture generator. Our light estimation is based on deep neural nets and determines the main light direction, light color, ambient color and an opacity parameter for the shadow texture. Our neural soft shadow method encodes object-based realistic soft shadows as light direction dependent textures in a small MLP. We show that our pipeline can be used to integrate objects into AR scenes in a new level of realism in real-time. Our models are small enough to run on current mobile devices. We achieve runtimes of 9ms for light estimation and 5ms for neural shadows on an iPhone 11 Pro.