CutDepth:Edge-aware Data Augmentation in Depth Estimation
This work addresses data scarcity for researchers and practitioners in monocular depth estimation, but it is incremental as it builds on existing augmentation techniques.
The paper tackles the challenge of limited training data in monocular depth estimation by proposing CutDepth, a data augmentation method that pastes parts of depth onto input images while preserving edge features, resulting in improved estimation accuracy, especially with few long-distance training data.
It is difficult to collect data on a large scale in a monocular depth estimation because the task requires the simultaneous acquisition of RGB images and depths. Data augmentation is thus important to this task. However, there has been little research on data augmentation for tasks such as monocular depth estimation, where the transformation is performed pixel by pixel. In this paper, we propose a data augmentation method, called CutDepth. In CutDepth, part of the depth is pasted onto an input image during training. The method extends variations data without destroying edge features. Experiments objectively and subjectively show that the proposed method outperforms conventional methods of data augmentation. The estimation accuracy is improved with CutDepth even though there are few training data at long distances.