Code for GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Pose (CVPR 2018)
Repo for "Graph-based Object Classification for Neuromorphic Vision Sensing" ICCV2019
Master's Thesis on Simultaneous Localization and Mapping in dynamic environments. Separately reconstructs both the static environment and the dynamic objects from it, such as cars.
DynaSLAM is a SLAM system robust in dynamic environments for monocular, stereo and RGB-D setups
Mask R-CNN for object detection and instance segmentation on Keras and TensorFlow
Unsupervised Learning of Monocular Depth Estimation and Visual Odometry with Deep Feature Reconstruction
Deeper Depth Prediction with Fully Convolutional Residual Networks(2016 IEEE 3D Vision)的pytorch实现