lion

Thank you @felixendres . RGBDSLAM can work, when I run ros master and RGBDSLAM in identical machine.But I find that windows of procedure seem shows single frame result fusion. When...

Typing "rostopic echo /kinect2/sd/image_color_rect/header",terminal shows: frame_id: kinect2_ir_optical_frame --- seq: 153 stamp: secs: 1468460536 nsecs: 759491121 Because I use libfreenect2 and iai_kinect2, so I change the rgbdslam.launch as follows: ``` ```...

ok, Thank you very much @felixendres

I have same problem

DeLF use ImageFolder to load data. https://pytorch.org/docs/stable/torchvision/datasets.html?highlight=imagefolder#torchvision.datasets.ImageFolder

https://github.com/tonyngjichun/SOLAR

@gizatt Is this problem solved?

@gizatt Sorry, I didn't understand what you meant

Vtk no special requirements, like: ``` In general VTK tries to be as portable as possible; the specific configurations below are known to work and tested. VTK supports the following...

And I want to know the difference between incremental and hybrid, is hybrid model can get better result of reconstruction? Thanks!