SuperDepth: Self-Supervised, Super-Resolved Monocular Depth Estimation
international conference on robotics and automation, 2019.
As a consequence of improved disparity estimation, we study its relation to the strongly correlated problem of pose estimation and show strong quantitative and qualitative performance compared to previous self-supervised pose estimation methods
Recent techniques in self-supervised monocular depth estimation are approaching the performance of supervised methods, but operate in low resolution only. We show that high resolution is key towards high-fidelity self-supervised monocular depth prediction. Inspired by recent deep learning methods for Single-Image Super-Resolution, we prop...More
PPT (Upload PPT)