Buratto Enrico, Simonetto Adriano, Agresti Gianluca, Schäfer Henrik, Zanuttigh Pietro
Department of Information Engineering, University of Padova, Via Gradenigo 6/b, 35131 Padova, Italy.
R&D Center Europe Stuttgart Laboratory 1, Sony Europe B.V., Hedelfinger Str. 61, 70327 Stuttgart, Germany.
Sensors (Basel). 2021 Mar 11;21(6):1962. doi: 10.3390/s21061962.
In this work, we propose a novel approach for correcting multi-path interference (MPI) in Time-of-Flight (ToF) cameras by estimating the direct and global components of the incoming light. MPI is an error source linked to the multiple reflections of light inside a scene; each sensor pixel receives information coming from different light paths which generally leads to an overestimation of the depth. We introduce a novel deep learning approach, which estimates the structure of the time-dependent scene impulse response and from it recovers a depth image with a reduced amount of MPI. The model consists of two main blocks: a predictive model that learns a compact encoded representation of the backscattering vector from the noisy input data and a fixed backscattering model which translates the encoded representation into the high dimensional light response. Experimental results on real data show the effectiveness of the proposed approach, which reaches state-of-the-art performances.
在这项工作中，我们提出了一种通过估计入射光的直接分量和全局分量来校正飞行时间（ToF）相机中多径干扰（MPI）的新方法。MPI是与场景内光的多次反射相关的误差源；每个传感器像素接收来自不同光路的信息，这通常会导致深度估计过高。我们引入了一种新颖的深度学习方法，该方法估计随时间变化的场景脉冲响应的结构，并从中恢复具有减少的MPI量的深度图像。该模型由两个主要模块组成：一个预测模型，它从噪声输入数据中学习反向散射向量的紧凑编码表示；以及一个固定的反向散射模型，它将编码表示转换为高维光响应。在真实数据上的实验结果表明了所提方法的有效性，该方法达到了当前的最优性能。
