StofNet: Super-resolution Time of Flight Network

TL;DR

StofNet introduces a novel super-resolution deep learning architecture tailored for precise Time of Flight depth sensing, improving accuracy and reliability under complex ambient conditions.

Contribution

The paper proposes a new architecture combining super-resolution with residual contraction blocks for enhanced ToF signal localization, and provides a comprehensive benchmark comparison including a new dataset.

Findings

StofNet outperforms six state-of-the-art methods in ToF depth sensing.

The model achieves higher precision and reliability with lower complexity.

The release of the SToF-Chirp dataset supports future research.

Abstract

Time of Flight (ToF) is a prevalent depth sensing technology in the fields of robotics, medical imaging, and non-destructive testing. Yet, ToF sensing faces challenges from complex ambient conditions making an inverse modelling from the sparse temporal information intractable. This paper highlights the potential of modern super-resolution techniques to learn varying surroundings for a reliable and accurate ToF detection. Unlike existing models, we tailor an architecture for sub-sample precise semi-global signal localization by combining super-resolution with an efficient residual contraction block to balance between fine signal details and large scale contextual information. We consolidate research on ToF by conducting a benchmark comparison against six state-of-the-art methods for which we employ two publicly available datasets. This includes the release of our SToF-Chirp dataset captured by an airborne ultrasound transducer. Results showcase the superior performance of our proposed StofNet in terms of precision, reliability and model complexity. Our code is available at https://github.com/hahnec/stofnet.