SC-DepthV3: Robust Self-Supervised Monocular Depth Estimation for Dynamic Scenes
SC-DepthV3: Robust Self-Supervised Monocular Depth Estimation for Dynamic Scenes
Self-supervised monocular depth estimation has shown impressive results in static scenes. It relies on the multi-view consistency assumption for training networks, however, that is violated in dynamic object regions and occlusions. Consequently, existing methods show poor accuracy in dynamic scenes, and the estimated depth map is blurred at object boundaries …