search

TRI-ML / packnet-sfm

TRI-ML Monocular Depth Estimation Repository
https://tri-ml.github.io/packnet-sfm/
MIT License
1.21k stars 241 forks source link

Velocity Supervision Loss #215

Open Adamqu199541 opened 2 years ago

Adamqu199541 commented 2 years ago

such a wonderful work,but i dont know how to calculate translation by instantaneous velocity measurements, because i just find

tx = scale packet.lon np.pi er / 180. ty = scale er \ np.log(np.tan((90. + packet.lat) np.pi / 360.)) tz = packet.alt t = np.array([tx, ty, tz]) in def pose_from_oxts_packet(raw_data, scale): these codes dont include instantaneous velocity measurements

Adamqu199541 commented 2 years ago

but in your paper you note that you introduce instantaneous velocity to calculate translation between two frame