We present a novel gradient-based multi-task learning (MTL) approach that balances training in multi-task systems by aligning the independent components of the training objective.
Our work shows that a model trained on this data along with conventional datasets can gain accuracy while predicting correct scene geometry.
Based on this finding, we propose LayerMatch scheme for approximating the representation of a GAN generator that can be used for unsupervised domain-specific pretraining.
Our second contribution is a novel training strategy that allows us to train on a semi-dense sensor data when the ground truth depth map is not available.
Ranked #1 on Depth Completion on Matterport3D
Monocular depth estimation is the task of obtaining a measure of distance for each pixel using a single image.