FIS-Nets: Full-image Supervised Networks for Monocular Depth Estimation
This work addresses depth estimation for computer vision applications, but it appears incremental as it builds on existing semi-supervised and supervised frameworks.
The paper tackles monocular depth estimation by proposing a semi-supervised architecture that combines unsupervised image consistency with supervised dense depth completion, using full-image depth as supervision and embedding ego-motion from navigation systems to improve accuracy, resulting in outperforming other approaches in evaluation.
This paper addresses the importance of full-image supervision for monocular depth estimation. We propose a semi-supervised architecture, which combines both unsupervised framework of using image consistency and supervised framework of dense depth completion. The latter provides full-image depth as supervision for the former. Ego-motion from navigation system is also embedded into the unsupervised framework as output supervision of an inner temporal transform network, making monocular depth estimation better. In the evaluation, we show that our proposed model outperforms other approaches on depth estimation.