Output of Demo scripts

[aakash26]

Hi, Thanks for uploading the code for this research paper. I am successfully able to run the demo code for nyu, however the output is a single depth image and same goes for demo_uncalibrated script where the entire video is provided as input. Shouldn't the output be multiple depth maps for different video frames or something similar as written in the paper?

[zachteed]

If you run with the --mode=global the depth maps for all frames will be predicted. You can also try the SLAM demos for predicting depth for longer sequences

[aakash26]

Hi @zachteed, Thanks for the reply. I ran the --mode=global, however I couldn't find all the depth maps for the frames in the output folder. There is only a single depth.png being created irrespective of what mode i run. Also, for uncalibrated videos is the same and is it possible to provide stereo video? Where would all the output depthmaps be stored?

Regards Aakash

[Tord-Zhang]

@zachteed Hi, I found that it requires the intrinsics of cameras to run the SLAM demo. Would it work without intrinsics? Just like the demo_uncalibrated.py?