Search Results for author:
Found 2 papers, 1 papers with code
Self-Supervised Monocular Depth Estimation of Untextured Indoor Rotated Scenes
Our experiments show that depth estimation is substantially improved on low-texture scenes, without any loss on textured scenes, when compared to Monodepth by Godard et al. Secondly, we show that training with an application's representative rotations, in both pitch and roll, is sufficient to significantly improve performance over the entire range of expected rotation.
How do neural networks see depth in single images?
We further show that MonoDepth's use of the vertical image position allows it to estimate the distance towards arbitrary obstacles, even those not appearing in the training set, but that it requires a strong edge at the ground contact point of the object to do so.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
