Learning 3D Shapes as Multi-Layered Height-maps using 2D Convolutional Networks

Learning 3D Shapes as Multi-Layered Height-maps using 2D Convolutional Networks
Kripasindhu Sarkar, Basavaraj Hampiholi, Kiran Varanasi, Didier Stricker
Computer Vision -- ECCV 2018 European Conference on Computer Vision (ECCV-2018), September 8-14, Munich, Germany

Abstract:
  We present a novel global representation of 3D shapes, suitable for the application of 2D CNNs. We represent 3D shapes as multi-layered height-maps (MLH) where at each grid location, we store multiple instances of height maps, thereby representing 3D shape detail that is hidden behind several layers of occlusion. We provide a novel view merging method for combining view dependent information (Eg. MLH descriptors) from multiple views. Because of the ability of using 2D CNNs, our method is highly memory efficient in terms of input resolution compared to the voxel based input. Together with MLH descriptors and our multi view merging we achieve the state-of-the-art result in classification on ModelNet dataset.

Other details

Please find the  -
  • Arxiv preprint of the paper here.
  • Code here.
  • MLH descriptors for ModelNet40 here
Keywords:
cnn, shape representation, multiview architecture