Real-time Light Estimation and Neural Soft Shadows for AR Indoor Scenarios

TL;DR

This paper introduces a real-time pipeline for AR indoor scene embedding that combines neural light estimation and soft shadow generation, enabling highly realistic virtual object integration on mobile devices.

Contribution

It presents a novel real-time AR pipeline with neural light estimation and soft shadow rendering optimized for mobile devices.

Findings

Achieves 9ms light estimation and 5ms shadow rendering on iPhone 11 Pro.

Provides realistic soft shadows with neural textures in real-time.

Enables more immersive AR experiences with improved visual realism.

Abstract

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.