Check out our CVPR'18 paper on weakly-supervised 3D shape completion — and let me know your opinion! @david_stutz


Alexandr Notchenko, Ermek Kapushev, Evgeny Burnaev. Sparse 3D Convolutional Neural Networks for Large-Scale Shape Retrieval. CoRR, 2016.

Notchenko present PySparseConvNet, a Python interface for SparseConvNet as introduced by Graham in []. They further conduct several experiments for shape retrieval and shape classification also investigating the influence of the resolution, see the paper for details.

  • [] B. Graham. Spatially-sparse convolutional neural networks. arXiv preprint arXiv:1409.6070, 2014.

What is your opinion on the summarized work? Or do you know related work that is of interest? Let me know your thoughts in the comments below or get in touch with me: