Question about MS evaluation about featdepth

[sconlyshootery]

We do this for mono because the scale is ambiguous, we use this operation to find a best matched scale to compare with GT, but for stereo, baseline is known, still using this operation will be unfair to compare with other stereo methods.

[sconlyshootery]

Unsupervised Learning of Depth and Ego-Motion from Video
this paper may help you get a better understanding of this setting.

[AttackonMuggle]

Thanks for your reply, and I have another question. Have you trained this code with only stereo data? My test results are not so good, but training on MS can bring improvement. I sincerely hope for your help.

[sconlyshootery]

Sorry, I didn't try on the Stereo data. This setting will not train posenet。

[sconlyshootery]

you can reopen it if you have further issues.