search

CVLAB-Unibo / Real-time-self-adaptive-deep-stereo

Code for "Real-time self-adaptive deep stereo" - CVPR 2019 (ORAL)
Apache License 2.0
420 stars 73 forks source link

collab example #68

Open Ademord opened 3 years ago

Ademord commented 3 years ago

hello, could you please provide a collab example where we input a sequence of video frames with depth information, just for inference?

AlessioTonioni commented 3 years ago

we do not have a colab example. But Stereo_Online_Adaptation.py does exactly what you described.

Ademord commented 3 years ago

Hello! Thank you for your reply. I think I might have slightly overlooked a detail and meant if there was a way to do what you do with monocular video ? (One camera in the agent, i could technically add two (one per eye?) but let me know what you think)

AlessioTonioni commented 3 years ago

This code is for a stereo camera, so you will need couples of synchronized frames coming from two cameras.