BertaBescos

DynaSLAM. DynaSLAM is a SLAM system robust in dynamic environments for monocular, stereo and RGB-D setups

EmptyCities_SLAM. Implementation for learning a mapping from urban images that contain dynamic objects to static realistic images suitable for SLAM

EmptyCities. Implementation for learning a mapping from images that contain dynamic objects in a city environment to static realistic images

PlotNeuralNet. Latex code for making neural networks diagrams

evaluate_ate_scale. Modified tool of the TUM RGB-D dataset that automatically computes the optimal scale factor that aligns trajectory and groundtruth. Useful to evaluate monocular VO/SLAM.