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

Kripasindhu Sarkar, Basavaraj Hampiholi, Kiran Varanasi +1

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 locatio…