Geometry-Aware Symmetric Domain Adaptation for Monocular Depth Estimation
This addresses the problem of limited ground truth depth labels for real-world images in computer vision, though it is incremental as it builds on existing domain adaptation techniques.
The paper tackles unsupervised monocular depth estimation by transferring knowledge from synthetic data with ground truth to real data, using a geometry-aware symmetric domain adaptation framework that incorporates epipolar geometry, resulting in high-quality depth maps with performance comparable to state-of-the-art methods.
Supervised depth estimation has achieved high accuracy due to the advanced deep network architectures. Since the groundtruth depth labels are hard to obtain, recent methods try to learn depth estimation networks in an unsupervised way by exploring unsupervised cues, which are effective but less reliable than true labels. An emerging way to resolve this dilemma is to transfer knowledge from synthetic images with ground truth depth via domain adaptation techniques. However, these approaches overlook specific geometric structure of the natural images in the target domain (i.e., real data), which is important for high-performing depth prediction. Motivated by the observation, we propose a geometry-aware symmetric domain adaptation framework (GASDA) to explore the labels in the synthetic data and epipolar geometry in the real data jointly. Moreover, by training two image style translators and depth estimators symmetrically in an end-to-end network, our model achieves better image style transfer and generates high-quality depth maps. The experimental results demonstrate the effectiveness of our proposed method and comparable performance against the state-of-the-art. Code will be publicly available at: https://github.com/sshan-zhao/GASDA.