Submitted by Chris Choy.

Submission data

Full nameMinkowskiNet34
DescriptionWe used the 3D variant of the MinkowskiNet34, which consists of 42 (34 + 8) convolution layers.

We used the Minkowski Engine ( to implement the network and it took ~1s to process an entire room in one go. The method will be made available to the public.
Input Data TypesUses Color        Uses 2D
Programming language(s)python/pytorch/C/C++/CUDA
Submission creation date27 Oct, 2018
Last edited20 Nov, 2018

3D semantic label results

Infoavg ioubathtubbedbookshelfcabinetchaircountercurtaindeskdoorfloorotherfurniturepicturerefrigeratorshower curtainsinksofatabletoiletwallwindow