Published at: International Symposium on Visual Computing (ISVC) 2019, pp 141-153
Abstract:
The development of Visual Inertial Odometry (VIO) systems such as ARKit and ARCore has brought smartphone Augmented Reality (AR) to mainstream. However, interactions between virtual objects and real objects are still limited due to the lack of 3D sensing capability. Recently, smartphone makers have been touting Time-of-Flight (ToF) cameras on their phones. ToF cameras can determine depth information in a photo using infrared light. By understanding the 3D structure of the scene, more AR capabilities can be enabled. In this paper, we propose practical methods to process ToF depth maps in real time and enable occlusion handling and collision detection for AR applications simultaneously. Our experimental results show real time performance and good visual quality for both occlusion rendering and collision detection.
Occlusion and Collision Aware Smartphone AR Using Time-of-Flight Camera