GCN-SLAM runing only use RGB?

[jinzhenmu]

The GCN-SLAM using the RGB-D. And it can runing only use RGB?

[DreamWaterFound]

Yes. You just need to hack some codes in Tracking::GrabImageMonocular() and overload Frame constructor with GCNextractor.

[szgy66]

Yes. You just need to hack some codes in Tracking::GrabImageMonocular() and overload Frame constructor with GCNextractor.

Can you tell the details?

[szgy66]

Yes. You just need to hack some codes in Tracking::GrabImageMonocular() and overload Frame constructor with GCNextractor.

Can you tell the details?

[leslieburke]

Yes. You just need to hack some codes in Tracking::GrabImageMonocular() and overload Frame constructor with GCNextractor.

Can you tell the details?

Hello，Did you solve it？

[cyizhuo]

Yes. You just need to hack some codes in Tracking::GrabImageMonocular() and overload Frame constructor with GCNextractor.

I'm currently hacking Track.cc and Frame.cc, already spent half a day now, the Tracking still returns a empty pose......

[wahaahaaaa]

是的。您只需要修改一些代码并Tracking::GrabImageMonocular()使用.Frame``GCNextractor

我目前正在破解Track.cc和Frame.cc，已经用了半天​​了，Tracking还是返回一个空的pose……

Did you succeed?

[cyizhuo]

是的。您只需要修改一些代码并Tracking::GrabImageMonocular()使用. FrameGCNextractor ``

我目前正在破解Track.cc和Frame.cc，已经用了半天​​了，Tracking还是返回一个空的pose……

Did you succeed?

Yes, I'll post my code later, but my result is that gcn works too slow on pure CPU, and it also lost track from time to time. I think we have to train our own feature model to achive better result. So I'm back to good old orb_slam3.

[wahaahaaaa]

是的。您只需要修改一些代码并Tracking::GrabImageMonocular()使用. FrameGCNextractor ``

我目前正在破解Track.cc和Frame.cc，已经用了半天​​了，Tracking还是返回一个空的pose……

Did you succeed?

Yes, I'll post my code later, but my result is that gcn works too slow on pure CPU, and it also lost track from time to time. I think we have to train our own feature model to achive better result. So I'm back to good old orb_slam3.

Thank you very much for your reply. When will the code be released?

[cyizhuo]

是的。您只需要修改一些代码并Tracking::GrabImageMonocular()使用. FrameGCNextractor ``

我目前正在破解Track.cc和Frame.cc，已经用了半天​​了，Tracking还是返回一个空的pose……

Did you succeed?

Yes, I'll post my code later, but my result is that gcn works too slow on pure CPU, and it also lost track from time to time. I think we have to train our own feature model to achive better result. So I'm back to good old orb_slam3.

Thank you very much for your reply. When will the code be released?

https://github.com/cyizhuo/GCNv2_SLAM_modified