“…• Temporal Continuity -temporal information is explicitly taken into account during training using both recurrent network feedback and gradients from a pre-trained frozen optical flow network. This leads to a novel scene understanding approach capable of temporally consistent geometric depth prediction and semantic scene segmentation whilst outperforming prior work across the domains of monocular depth estimation [8,25,29,49,83,87], completion [9,36,50,82] and semantic segmentation [10,17,40,52,53,59,74,75,86].…”