ReflecTrace: Touchless Hover Interaction on Commodity Smartphones via Corneal Reflection

We propose an approach to detect finger hover inputs on a smartphone screen using corneal reflection images captured by the device’s built-in front camera. This method requires no external sensors or hardware, enabling hover input detection in the near-screen space that is not directly visible to the camera. By leveraging a convolutional neural network (CNN), we estimate the two-dimensional position of a hovering finger and classify it into a predefined screen grid. Experimental results show that our model achieves approximately 95% accuracy for coarse grids and maintains over 88% accuracy for finer divisions. Furthermore, our system demonstrates real-time processing capability with an end-to-end latency of approximately 22 ms on a standard smartphone. These findings highlight the practical feasibility of camera-only hover sensing and suggest a wide range of touchless interaction applications, enabling touchless interaction when touch is undesirable, pre-touch UI adaptation, and accessibility support on commodity mobile devices.