A comparison of scene flow estimation paradigms

Iraklis Tsekourakis, Philippos Mordohai

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

This paper presents a comparison between two core paradigms for computing scene flow from multi-view videos of dynamic scenes. In both approaches, shape and motion estimation are decoupled, in accordance to a large segment of the relevant literature. The first approach is faster and considers only one optical flow field and the depth difference between pixels in consecutive frames to generate a dense scene flow estimate. The second approach is more robust to outliers by considering multiple optical flow fields to generate scene flow. Our goal is to compare the isolated fundamental scene flow estimation methods, without using any post-processing, or optimization. We assess the accuracy of the two methods performing two tests: an optical flow prediction, and a future image prediction, both on a novel view. This is the first quantitative evaluation of scene flow estimation on real imagery of dynamic scenes, in absence of ground truth data.

Original languageEnglish
Title of host publicationRepresentations, Analysis and Recognition of Shape and Motion from Imaging Data - 7th International Workshop, RFMI 2017, Revised Selected Papers
EditorsFaouzi Ghorbel, Boulbaba Ben Amor, Liming Chen
Pages3-19
Number of pages17
DOIs
StatePublished - 2019
Event7th International Workshop on Representations, Analysis and Recognition of Shape and Motion from Imaging Data, RFMI 2017 - Savoie, France
Duration: 17 Dec 201720 Dec 2017

Publication series

NameCommunications in Computer and Information Science
Volume842
ISSN (Print)1865-0929
ISSN (Electronic)1865-0937

Conference

Conference7th International Workshop on Representations, Analysis and Recognition of Shape and Motion from Imaging Data, RFMI 2017
Country/TerritoryFrance
CitySavoie
Period17/12/1720/12/17

Fingerprint

Dive into the research topics of 'A comparison of scene flow estimation paradigms'. Together they form a unique fingerprint.

Cite this