TCC-Det: Temporarily Consistent Cues for Weakly-Supervised 3D Detection

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F25%3A00377724" target="_blank" >RIV/68407700:21230/25:00377724 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.1007/978-3-031-73347-5_8" target="_blank" >https://doi.org/10.1007/978-3-031-73347-5_8</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-031-73347-5_8" target="_blank" >10.1007/978-3-031-73347-5_8</a>

Jazyk výsledku

angličtina

Název v původním jazyce

TCC-Det: Temporarily Consistent Cues for Weakly-Supervised 3D Detection

Popis výsledku v původním jazyce

Accurate object detection in LiDAR point clouds is a key prerequisite of robust and safe autonomous driving and robotics applications. Training the 3D object detectors currently involves the need to manually annotate vasts amounts of training data, which is very time-consuming and costly. As a result, the amount of annotated training data readily available is limited, and moreover these annotated datasets likely do not contain edge-case or otherwise rare instances, simply because the probability of them occurring in such a small dataset is low. In this paper, we propose a method to train 3D object detector without any need for manual annotations, by exploiting existing off-the-shelf vision components and by using the consistency of the world around us. The method can therefore be used to train a 3D detector by only collecting sensor recordings in the real world, which is extremely cheap and allows training using orders of magnitude more data than traditional fully-supervised methods. The method is evaluated on KITTI and Waymo Open datasets, where it outperforms all previous weakly-supervised methods and where it narrows the gap when compared to methods using human 3D labels. The source code of our method is publicly available at https://www.github.com/jskvrna/TCC-Det.

Název v anglickém jazyce

TCC-Det: Temporarily Consistent Cues for Weakly-Supervised 3D Detection

Popis výsledku anglicky

Accurate object detection in LiDAR point clouds is a key prerequisite of robust and safe autonomous driving and robotics applications. Training the 3D object detectors currently involves the need to manually annotate vasts amounts of training data, which is very time-consuming and costly. As a result, the amount of annotated training data readily available is limited, and moreover these annotated datasets likely do not contain edge-case or otherwise rare instances, simply because the probability of them occurring in such a small dataset is low. In this paper, we propose a method to train 3D object detector without any need for manual annotations, by exploiting existing off-the-shelf vision components and by using the consistency of the world around us. The method can therefore be used to train a 3D detector by only collecting sensor recordings in the real world, which is extremely cheap and allows training using orders of magnitude more data than traditional fully-supervised methods. The method is evaluated on KITTI and Waymo Open datasets, where it outperforms all previous weakly-supervised methods and where it narrows the gap when compared to methods using human 3D labels. The source code of our method is publicly available at https://www.github.com/jskvrna/TCC-Det.

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

Výsledek vznikl pri realizaci vícero projektů. Více informací v záložce Projekty.

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2025

Kód důvěrnosti údajů

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

Název statě ve sborníku

Computer Vision – ECCV 2024, Part XXVI

ISBN

978-3-031-73346-8

ISSN

0302-9743

e-ISSN

1611-3349

Počet stran výsledku

17

Strana od-do

129-145

Název nakladatele

Springer, Cham

Místo vydání

—

Místo konání akce

Milano

Datum konání akce

29. 9. 2024

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

001352789800008