In monocular depth estimation, uncertainty estimation approaches mainly target the data uncertainty introduced by image noise. In contrast to prior work, we address the uncertainty due to lack of knowledge, which is relevant for the detection of data not represented by the training distribution, the so-called out-of-distribution (OOD) data. Motivated by anomaly detection, we propose to detect OOD images from an encoder-decoder depth estimation model based on the reconstruction error. Given the features extracted with the fixed depth encoder, we train an image decoder for image reconstruction using only in-distribution data. Consequently, OOD images result in a high reconstruction error, which we use to distinguish between in- and out-of-distribution samples. We built our experiments on the standard NYU Depth V2 and KITTI benchmarks as in-distribution data. Our post hoc method performs astonishingly well on different models and outperforms existing uncertainty estimation approaches without modifying the trained encoder-decoder depth estimation model.

翻译：在单目深度估计中，不确定性估计方法主要针对图像噪声引入的数据不确定性。与以往工作不同，我们关注由于知识缺失所导致的不确定性，这关乎检测训练分布中未出现的数据——即所谓的分布外数据。受异常检测启发，我们提出基于重建误差从编码器-解码器深度估计模型中检测分布外图像。利用固定深度编码器提取的特征，我们仅使用分布内数据训练用于图像重建的解码器。由此，分布外图像会产生较高的重建误差，我们据此区分分布内与分布外样本。我们的实验以标准NYU Depth V2和KITTI基准作为分布内数据集。该事后处理方法在不同模型上表现卓越，且无需修改已训练的编码器-解码器深度估计模型，即可优于现有的不确定性估计方法。