基于结构化损失的单目深度估计算法研究

Research on Monocular Depth Estimation Algorithm Based on Structured Loss

为了提高单目图像深度估计的精度,针对图像中几何形状无法准确预测以及边缘模糊的问题,该文提出了一种基于多尺度结构相似度和梯度匹配的单目深度估计算法,利用多尺度结构相似度损失和尺度不变梯度匹配损失组成联合结构化损失,对相对深度点对进行排序来实现单目深度估计,实现了对图像中几何形状的准确预测,减小了边缘模糊,提高了深度预测精度。在Ibims、NYUDv2、DIODE、Sintel 4个不同类型的数据集进行了数值实验和主观评测,结果表明该算法降低了深度预测误差,有效提高了预测的准确性,并具有一定的泛化性能。

This paper proposes a monocular depth estimation algorithm based on multi-scale structure similarity and gradient matching for improving the accuracy of monocular image depth estimation and solving the problems of inaccurate prediction of geometric shapes and blurred edges in the image.In this algorithm,a joint structured loss is formed by using multi-scale structure similarity degree loss and scale-invariant gradient matching loss.The relative depth points are sorted to achieve monocular depth estimation,which realizes accurate prediction of geometric shapes in the image,reduces edge blur,and improves depth prediction accuracy.Numerical experiments and subjective evaluations are performed on four different types of data sets:Ibims,NYUDv2,DIODE,and Sintel.The results show that the algorithm significantly reduces the depth prediction error,effectively improves the accuracy of the prediction,and has a certain generalization performance.