Exploring the Impacts from Datasets to Monocular Depth Estimation (MDE) Models with MineNavi
This addresses the data scarcity issue in computer vision for domain-specific applications like aircraft navigation, but it is incremental as it builds on existing synthetic data approaches.
The authors tackled the problem of limited annotated data for dense estimation tasks like monocular depth estimation by proposing MineNavi, a synthetic dataset generation method for aircraft navigation, which improved model performance and sped up convergence on real data.
Current computer vision tasks based on deep learning require a huge amount of data with annotations for model training or testing, especially in some dense estimation tasks, such as optical flow segmentation and depth estimation. In practice, manual labeling for dense estimation tasks is very difficult or even impossible, and the scenes of the dataset are often restricted to a small range, which dramatically limits the development of the community. To overcome this deficiency, we propose a synthetic dataset generation method to obtain the expandable dataset without burdensome manual workforce. By this method, we construct a dataset called MineNavi containing video footages from first-perspective-view of the aircraft matched with accurate ground truth for depth estimation in aircraft navigation application. We also provide quantitative experiments to prove that pre-training via our MineNavi dataset can improve the performance of depth estimation model and speed up the convergence of the model on real scene data. Since the synthetic dataset has a similar effect to the real-world dataset in the training process of deep model, we also provide additional experiments with monocular depth estimation method to demonstrate the impact of various factors in our dataset such as lighting conditions and motion mode.