Junbang Liang

Jul 24, 2024 | amazon.science | Muhammad Khan |Junbang Liang |Chun-Kai Wang |Shan Yang

Pre-training has been an important ingredient in developing strong monocular depth estimation models in recent years. For instance, self-supervised learning (SSL) is particularly effective by alleviating the need for large datasets with dense ground-truth depth maps. However, despite these improvements, our study reveals that the later layers of the SOTA SSL method are actually suboptimal.