Time-to-Label: Temporal Consistency for Self-Supervised Monocular 3D Object Detection

Monocular 3D object detection continues to attract attention due to the cost benefits and wider availability of RGB cameras. Despite the recent advances and the ability to acquire data at scale, annotation cost and complexity still limit the size of 3D object detection datasets in the supervised set...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:IEEE robotics and automation letters Ročník 7; číslo 4; s. 8988 - 8995
Hlavní autori: Mouawad, Issa, Brasch, Nikolas, Manhardt, Fabian, Tombari, Federico, Odone, Francesca
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Piscataway IEEE 01.10.2022
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Predmet:
Annotations
computer vision for transportation
Consistency
Labels
Laser radar
Object detection
Object recognition
Quality assessment
segmentation and categorization
Shape
Solid modeling
Space perception
Task analysis
Three dimensional models
Three-dimensional displays
Training
ISSN:2377-3766, 2377-3766
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:Monocular 3D object detection continues to attract attention due to the cost benefits and wider availability of RGB cameras. Despite the recent advances and the ability to acquire data at scale, annotation cost and complexity still limit the size of 3D object detection datasets in the supervised settings. Self-supervised methods, on the other hand, aim at training deep networks relying on pretext tasks or various consistency constraints. Moreover, other 3D perception tasks (such as depth estimation) have shown the benefits of temporal priors as a self-supervision signal. In this work, we argue that the temporal consistency on the level of object poses, provides an important supervision signal given the strong prior on physical motion. Specifically, we propose a self-supervised loss which uses this consistency, in addition to render-and-compare losses defined on lidar point clouds, to refine noisy pose predictions and derive high-quality pseudo labels. To assess the effectiveness of the proposed method, we finetune a synthetically trained monocular 3D object detection model using the pseudo-labels that we generated on real data. Evaluation on the standard KITTI3D benchmark demonstrates that our method reaches competitive performance compared to other monocular self-supervised and supervised methods.
Bibliografia:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2377-3766
2377-3766
DOI:10.1109/LRA.2022.3188882