Scalable full flow with learned binary descriptors

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F17%3A00315701" target="_blank" >RIV/68407700:21230/17:00315701 - isvavai.cz</a>

Výsledek na webu

<a href="http://dx.doi.org/10.1007/978-3-319-66709-6_26" target="_blank" >http://dx.doi.org/10.1007/978-3-319-66709-6_26</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-319-66709-6_26" target="_blank" >10.1007/978-3-319-66709-6_26</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Scalable full flow with learned binary descriptors

Popis výsledku v původním jazyce

We propose a method for large displacement optical flow in which local matching costs are learned by a convolutional neural network (CNN) and a smoothness prior is imposed by a conditional random field (CRF). We tackle the computation- and memory-intensive operations on the 4D cost volume by a min-projection which reduces memory complexity from quadratic to linear and binary descriptors for efficient matching. This enables evaluation of the cost on the fly and allows to perform learning and CRF inference on high resolution images without ever storing the 4D cost volume. To address the problem of learning binary descriptors we propose a new hybrid learning scheme. In contrast to current state of the art approaches for learning binary CNNs we can compute the exact non-zero gradient within our model. We compare several methods for training binary descriptors and show results on public available benchmarks.

Název v anglickém jazyce

Scalable full flow with learned binary descriptors

Popis výsledku anglicky

We propose a method for large displacement optical flow in which local matching costs are learned by a convolutional neural network (CNN) and a smoothness prior is imposed by a conditional random field (CRF). We tackle the computation- and memory-intensive operations on the 4D cost volume by a min-projection which reduces memory complexity from quadratic to linear and binary descriptors for efficient matching. This enables evaluation of the cost on the fly and allows to perform learning and CRF inference on high resolution images without ever storing the 4D cost volume. To address the problem of learning binary descriptors we propose a new hybrid learning scheme. In contrast to current state of the art approaches for learning binary CNNs we can compute the exact non-zero gradient within our model. We compare several methods for training binary descriptors and show results on public available benchmarks.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

N - Vyzkumna aktivita podporovana z neverejnych zdroju

Rok uplatnění

2017

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

39th German Conference on Pattern Recognition

ISBN

978-3-319-66708-9

ISSN

0302-9743

e-ISSN

—

Počet stran výsledku

12

Strana od-do

321-332

Název nakladatele

Springer, Cham

Místo vydání

—

Místo konání akce

Basel

Datum konání akce

12. 9. 2017

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—