Continual Occlusion and Optical Flow Estimation

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F19%3A00332673" target="_blank" >RIV/68407700:21230/19:00332673 - isvavai.cz</a>

Výsledek na webu

<a href="https://link.springer.com/content/pdf/10.1007/978-3-030-20870-7_10.pdf" target="_blank" >https://link.springer.com/content/pdf/10.1007/978-3-030-20870-7_10.pdf</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-030-20870-7_10" target="_blank" >10.1007/978-3-030-20870-7_10</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Continual Occlusion and Optical Flow Estimation

Popis výsledku v původním jazyce

Two optical flow estimation problems are addressed: (i) occlusion estimation and handling, and (ii) estimation from image sequences longer than two frames. The proposed ContinualFlow method estimates occlusions before flow, avoiding the use of flow corrupted by occlusions for their estimation. We show that providing occlusion masks as an additional input to flow estimation improves the standard performance metric by more than 25% on both KITTI and Sintel. As a second contribution, a novel method for incorporating information from past frames into flow estimation is introduced. The previous frame flow serves as an input to occlusion estimation and as a prior in occluded regions, i.e. those without visual correspondences. By continually using the previous frame flow, ContinualFlow performance improves further by 18% on KITTI and 7% on Sintel, achieving top performance on KITTI and Sintel. 2019, Springer Nature Switzerland AG.

Název v anglickém jazyce

Continual Occlusion and Optical Flow Estimation

Popis výsledku anglicky

Two optical flow estimation problems are addressed: (i) occlusion estimation and handling, and (ii) estimation from image sequences longer than two frames. The proposed ContinualFlow method estimates occlusions before flow, avoiding the use of flow corrupted by occlusions for their estimation. We show that providing occlusion masks as an additional input to flow estimation improves the standard performance metric by more than 25% on both KITTI and Sintel. As a second contribution, a novel method for incorporating information from past frames into flow estimation is introduced. The previous frame flow serves as an input to occlusion estimation and as a prior in occluded regions, i.e. those without visual correspondences. By continually using the previous frame flow, ContinualFlow performance improves further by 18% on KITTI and 7% on Sintel, achieving top performance on KITTI and Sintel. 2019, Springer Nature Switzerland AG.

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

<a href="/cs/project/EF16_019%2F0000765" target="_blank" >EF16_019/0000765: Výzkumné centrum informatiky</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2019

Kód důvěrnosti údajů

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

Název statě ve sborníku

ACCV 2018: Proceedings of the 14th Asian Conference on Computer Vision, Part IV

ISBN

978-3-030-20869-1

ISSN

0302-9743

e-ISSN

1611-3349

Počet stran výsledku

16

Strana od-do

159-174

Název nakladatele

Springer

Místo vydání

Cham

Místo konání akce

Perth

Datum konání akce

4. 12. 2018

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000490895400010