1 code implementation • 24 Jun 2021 • Benjamin Keltjens, Tom van Dijk, Guido de Croon
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.
no code implementations • ICCV 2019 • Tom van Dijk, Guido C. H. E. de Croon
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.