Torch + python implementation of Deep 6-DOF Tracking

The code to parse a ply file is not provided, this framework needs an implementation of plyparser.py

• Paper
• Dataset and project page
• Python code to download/load the data

Run:

python generate_synthetic_data.py config_file.json

• cv2
• numpy (tested with 1.13.3)
• tqdm
• pyOpenGL
• glfw
• numpngw

see this example file

Run:

python generate_real_data.py config_file.json

• cv2
• numpy (tested with 1.13.3)
• tqdm
• pyOpenGL
• glfw
• numpngw

see this example file

Run:

python train.py config_file.json

• Hugh Perkins's pytorch
• scipy, skimage, numpy (tested with 1.13.3)
• tqdm
• numpngw
• slackclient (could be removed)

see this example file

Will run the tracker with a sensor (kinect 2)

python test_sensor.py config_file.json

Will run the tracker on a sequence (folder) and save the error in a file

python test_sequence.py config_file.json

• cv2
• numpy (tested with 1.13.3)
• Hugh Perkins's pytorch
• pyOpenGL
• glfw
• numpngw
• pyfreenect2 (for Kinect2 sensor)

see this example file