Self-supervised Learning for Single View Depth and Surface Normal Estimation
This work addresses the challenge of 3D scene understanding for computer vision applications, offering an incremental improvement by integrating surface orientation into depth estimation.
The paper tackles the problem of predicting depth and surface normals from a single image by proposing a self-supervised learning framework that uses depth-normal consistency as a soft constraint, resulting in state-of-the-art normal predictions and a depth network that outperforms traditional methods by a large margin on the KITTI benchmark.
In this work we present a self-supervised learning framework to simultaneously train two Convolutional Neural Networks (CNNs) to predict depth and surface normals from a single image. In contrast to most existing frameworks which represent outdoor scenes as fronto-parallel planes at piece-wise smooth depth, we propose to predict depth with surface orientation while assuming that natural scenes have piece-wise smooth normals. We show that a simple depth-normal consistency as a soft-constraint on the predictions is sufficient and effective for training both these networks simultaneously. The trained normal network provides state-of-the-art predictions while the depth network, relying on much realistic smooth normal assumption, outperforms the traditional self-supervised depth prediction network by a large margin on the KITTI benchmark. Demo video: https://youtu.be/ZD-ZRsw7hdM