GeoNet: Geometric Neural Network for Joint Depth and Surface Normal Estimation
GeoNet++: Interative Geometric Neural network with Edge-aware Refinement Joint Depth and Surface Normal Estimation. (In preparation)
Required python libraries: Tensorflow (>=1.2) + Scipy + Numpy + Scipy + OpenCV.
Tested in Ubuntu + Intel i7 CPU + Nvidia Titan X (Pascal) with Cuda (>=8.0) and CuDNN (>=5.0). CPU mode should also work with minor changes.
-
Download pretrained model data, initialization model, and trained model from "https://drive.google.com/open?id=1o2t8735acVf2cLSCS6URkNViOB7mdb-Q"
-
tar xvzf GeoNet.tar.gz
-
Merge files into the Repo according to the file name.
-
Run 'code.py'
-
Evaluation: cd eval & run 'test_depth.m' for depth evaluation and run 'test_norm.py' for normal evaluation.
Training code already included. Detailed data preparation & running procedure will be updated soon.