In monocular depth estimation, disturbances in the image context, like moving objects or reflecting materials, can easily lead to erroneous predictions. For that reason, uncertainty estimates for each pixel are necessary, in particular for safety-critical applications such as automated driving. We propose a post hoc uncertainty estimation approach for an already trained and thus fixed depth estimation model, represented by a deep neural network. The uncertainty is estimated with the gradients which are extracted with an auxiliary loss function. To avoid relying on ground-truth information for the loss definition, we present an auxiliary loss function based on the correspondence of the depth prediction for an image and its horizontally flipped counterpart. Our approach achieves state-of-the-art uncertainty estimation results on the KITTI and NYU Depth V2 benchmarks without the need to retrain the neural network. Models and code are publicly available at https://github.com/jhornauer/GrUMoDepth.
翻译:在单心深度估计中,图像环境的扰动,如移动物体或反射材料,很容易导致错误预测。因此,每个像素的不确定性估计是必要的,特别是对于安全关键应用,例如自动驾驶。我们建议对已经受过训练并因此固定的深度估计模型采取临时不确定性估计办法,由深神经网络代表。用附带损失功能提取的梯度来估计不确定性。为避免依赖地面真实信息确定损失定义,我们根据深度预测对应图像及其横向翻转的对应方的对应词提出附带损失功能。我们的方法在KITTI和NYU深度V2基准上实现了最先进的不确定性估计结果,而无需对神经网络进行再培训。模型和代码可在https://github.com/jhornauer/GrUMoDepteh上公开查阅。