← Search

Kiran Varanasi

2 accepted papers

2018

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

ECCV 2018poster

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…

Cited by 40SourcePDFScholar
2017

CNN-Based Patch Matching for Optical Flow With Thresholded Hinge Embedding Loss

CVPR 2017poster

Learning based approaches have not yet achieved their full potential in optical flow estimation, where their performance still trails heuristic approaches. In this paper, we present a CNN based patch matching approach for optical flow estimation. An important contribution of our approach is a novel…

Cited by 149PDFScholar