Mask-ToF: Learning Microlens Masks for Flying Pixel Correction in Time-of-Flight Imaging

TL;DR

Mask-ToF introduces a novel microlens mask learning approach that significantly reduces flying pixels in ToF imaging by encoding scene geometry into sensor measurements, improving depth accuracy.

Contribution

The paper presents a new method to learn microlens masks for ToF sensors, enabling scene-aware modulation to reduce artifacts without retraining on real data.

Findings

Halves flying pixel counts in ToF images.

Generalizes well from simulation to real hardware.

Achieves high-fidelity depth reconstructions.

Abstract

We introduce Mask-ToF, a method to reduce flying pixels (FP) in time-of-flight (ToF) depth captures. FPs are pervasive artifacts which occur around depth edges, where light paths from both an object and its background are integrated over the aperture. This light mixes at a sensor pixel to produce erroneous depth estimates, which can adversely affect downstream 3D vision tasks. Mask-ToF starts at the source of these FPs, learning a microlens-level occlusion mask which effectively creates a custom-shaped sub-aperture for each sensor pixel. This modulates the selection of foreground and background light mixtures on a per-pixel basis and thereby encodes scene geometric information directly into the ToF measurements. We develop a differentiable ToF simulator to jointly train a convolutional neural network to decode this information and produce high-fidelity, low-FP depth reconstructions. We test the effectiveness of Mask-ToF on a simulated light field dataset and validate the method with an experimental prototype. To this end, we manufacture the learned amplitude mask and design an optical relay system to virtually place it on a high-resolution ToF sensor. We find that Mask-ToF generalizes well to real data without retraining, cutting FP counts in half.