Imperial College London


Faculty of EngineeringDepartment of Electrical and Electronic Engineering




+44 (0)20 7594 6173c.ciliberto CV




1003Electrical EngineeringSouth Kensington Campus






BibTex format

author = {Fanello, SR and Valentin, J and Kowdle, A and Rhemann, C and Tankovich, V and Ciliberto, C and Davidson, P and Izadi, S},
doi = {10.1109/ICCV.2017.418},
pages = {3894--3903},
title = {Low Compute and Fully Parallel Computer Vision with HashMatch},
url = {},
year = {2017}

RIS format (EndNote, RefMan)

AB - © 2017 IEEE. Numerous computer vision problems such as stereo depth estimation, object-class segmentation and fore-ground/background segmentation can be formulated as per-pixel image labeling tasks. Given one or many images as input, the desired output of these methods is usually a spatially smooth assignment of labels. The large amount of such computer vision problems has lead to significant research efforts, with the state of art moving from CRF-based approaches to deep CNNs and more recently, hybrids of the two. Although these approaches have significantly advanced the state of the art, the vast majority has solely focused on improving quantitative results and are not designed for low-compute scenarios. In this paper, we present a new general framework for a variety of computer vision labeling tasks, called HashMatch. Our approach is designed to be both fully parallel, i.e. each pixel is independently processed, and low-compute, with a model complexity an order of magnitude less than existing CNN and CRF-based approaches. We evaluate HashMatch extensively on several problems such as disparity estimation, image retrieval, feature approximation and background subtraction, for which HashMatch achieves high computational efficiency while producing high quality results.
AU - Fanello,SR
AU - Valentin,J
AU - Kowdle,A
AU - Rhemann,C
AU - Tankovich,V
AU - Ciliberto,C
AU - Davidson,P
AU - Izadi,S
DO - 10.1109/ICCV.2017.418
EP - 3903
PY - 2017///
SN - 1550-5499
SP - 3894
TI - Low Compute and Fully Parallel Computer Vision with HashMatch
UR -
ER -