Pose-graph via Adaptive Image Re-ordering

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21110%2F22%3A00361443" target="_blank" >RIV/68407700:21110/22:00361443 - isvavai.cz</a>

Nalezeny alternativní kódy

RIV/68407700:21230/22:00361443

Výsledek na webu

<a href="https://bmvc2022.mpi-inf.mpg.de/0127.pdf" target="_blank" >https://bmvc2022.mpi-inf.mpg.de/0127.pdf</a>

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Pose-graph via Adaptive Image Re-ordering

Popis výsledku v původním jazyce

We introduce novel methods that speed up the pose-graph generation for global Structure-from-Motion algorithms. We replace the widely used ``accept-or-reject'' strategy for image pairs, where often thousands of RANSAC iterations are wasted on pairs with low inlier ratio or on non-matchable ones. The new algorithm exploits the fact that every unsuccessful RANSAC iteration reduces the probability of an image pair being matchable, i.e., it reduces its inlier ratio expectation. The method always selects the most promising pair for matching. While running RANSAC on the pair, it updates the distribution of its inlier ratio probability in a principled way via a Bayesian approach. Once the expected inlier ratio drops below an adaptive threshold, the method puts back the pair in the processing queue ordered by the updated inlier ratio expectations. The algorithms are tested on more than 600k real image pairs. They accelerate the pose-graph generation by an order-of-magnitude on average. The code will be made available.

Název v anglickém jazyce

Pose-graph via Adaptive Image Re-ordering

Popis výsledku anglicky

We introduce novel methods that speed up the pose-graph generation for global Structure-from-Motion algorithms. We replace the widely used ``accept-or-reject'' strategy for image pairs, where often thousands of RANSAC iterations are wasted on pairs with low inlier ratio or on non-matchable ones. The new algorithm exploits the fact that every unsuccessful RANSAC iteration reduces the probability of an image pair being matchable, i.e., it reduces its inlier ratio expectation. The method always selects the most promising pair for matching. While running RANSAC on the pair, it updates the distribution of its inlier ratio probability in a principled way via a Bayesian approach. Once the expected inlier ratio drops below an adaptive threshold, the method puts back the pair in the processing queue ordered by the updated inlier ratio expectations. The algorithms are tested on more than 600k real image pairs. They accelerate the pose-graph generation by an order-of-magnitude on average. The code will be made available.

Druh

O - Ostatní výsledky

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)

Rok uplatnění

2022

Kód důvěrnosti údajů

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