LightDepth: A Resource Efficient Depth Estimation Approach for Dealing with Ground Truth Sparsity via Curriculum Learning. (arXiv:2211.08608v2 [cs.CV] UPDATED)

Advances in neural networks enable tackling complex computer vision tasks
such as depth estimation of outdoor scenes at unprecedented accuracy. Promising
research has been done on depth estimation. However, current efforts are
computationally resource-intensive and do not consider the resource constraints
of autonomous devices, such as robots and drones. In this work, we present a
fast and battery-efficient approach for depth estimation. Our approach devises
model-agnostic curriculum-based learning for depth estimation. Our experiments
show that the accuracy of our model …

arxiv curriculum curriculum learning sparsity