Generalized Differentiable RANSAC

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F23%3A00370527" target="_blank" >RIV/68407700:21230/23:00370527 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.1109/ICCV51070.2023.01618" target="_blank" >https://doi.org/10.1109/ICCV51070.2023.01618</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/ICCV51070.2023.01618" target="_blank" >10.1109/ICCV51070.2023.01618</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Generalized Differentiable RANSAC

Popis výsledku v původním jazyce

We propose del-RANSAC, a generalized differentiable RANSAC that allows learning the entire randomized robust estimation pipeline. The proposed approach enables the use of relaxation techniques for estimating the gradients in the sampling distribution, which are then propagated through a differentiable solver. The trainable quality function marginalizes over the scores from all the models estimated within del-RANSAC to guide the network learning accurate and useful inlier probabilities or to train feature detection and matching networks. Our method directly maximizes the probability of drawing a good hypothesis, allowing us to learn better sampling distributions. We test del-RANSAC on various real-world scenarios on fundamental and essential matrix estimation, and 3D point cloud registration, outdoors and indoors, with handcrafted and learning-based features. It is superior to the state-of-the-art in terms of accuracy while running at a similar speed to its less accurate alternatives. The code and trained models are available at https://github.com/weitong8591/differentiable_ransac.

Název v anglickém jazyce

Generalized Differentiable RANSAC

Popis výsledku anglicky

We propose del-RANSAC, a generalized differentiable RANSAC that allows learning the entire randomized robust estimation pipeline. The proposed approach enables the use of relaxation techniques for estimating the gradients in the sampling distribution, which are then propagated through a differentiable solver. The trainable quality function marginalizes over the scores from all the models estimated within del-RANSAC to guide the network learning accurate and useful inlier probabilities or to train feature detection and matching networks. Our method directly maximizes the probability of drawing a good hypothesis, allowing us to learn better sampling distributions. We test del-RANSAC on various real-world scenarios on fundamental and essential matrix estimation, and 3D point cloud registration, outdoors and indoors, with handcrafted and learning-based features. It is superior to the state-of-the-art in terms of accuracy while running at a similar speed to its less accurate alternatives. The code and trained models are available at https://github.com/weitong8591/differentiable_ransac.

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

2023

Kód důvěrnosti údajů

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

Název statě ve sborníku

ICCV2023: Proceedings of the International Conference on Computer Vision

ISBN

979-8-3503-0719-1

ISSN

1550-5499

e-ISSN

2380-7504

Počet stran výsledku

12

Strana od-do

17603-17614

Název nakladatele

IEEE

Místo vydání

Piscataway

Místo konání akce

Paris

Datum konání akce

2. 10. 2023

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

001169500502021