In this paper we propose an approach for monocular 3D object detection from a single RGB image, which leverages a novel disentangling transformation for 2D and 3D detection losses and a novel, self-supervised confidence score for 3D bounding boxes. Our proposed loss disentanglement has the twofold advantage of simplifying the training dynamics in the presence of losses with complex interactions of parameters, and sidestepping the issue of balancing independent regression terms. Our solution overcomes these issues by isolating the contribution made by groups of parameters to a given loss, without changing its nature. We further apply loss disentanglement to another novel, signed Intersection-over-Union criterion-driven loss for improving 2D detection results. Besides our methodological innovations, we critically review the AP metric used in KITTI3D, which emerged as the most important dataset for comparing 3D detection results. We identify and resolve a flaw in the 11-point interpolated AP metric, affecting all previously published detection results and particularly biases the results of monocular 3D detection. We provide extensive experimental evaluations and ablation studies and set a new state-of-the-art on the KITTI3D Car class.

Disentangling Monocular 3D Object Detection / Simonelli, A.; Bulo, S. R.; Porzi, L.; Lopez-Antequera, M.; Kontschieder, P.. - ELETTRONICO. - 2019-:(2019), pp. 1991-1999. (Intervento presentato al convegno 17th IEEE/CVF International Conference on Computer Vision, ICCV 2019 tenutosi a kor nel 2019) [10.1109/ICCV.2019.00208].

Disentangling Monocular 3D Object Detection

Simonelli A.;
2019-01-01

Abstract

In this paper we propose an approach for monocular 3D object detection from a single RGB image, which leverages a novel disentangling transformation for 2D and 3D detection losses and a novel, self-supervised confidence score for 3D bounding boxes. Our proposed loss disentanglement has the twofold advantage of simplifying the training dynamics in the presence of losses with complex interactions of parameters, and sidestepping the issue of balancing independent regression terms. Our solution overcomes these issues by isolating the contribution made by groups of parameters to a given loss, without changing its nature. We further apply loss disentanglement to another novel, signed Intersection-over-Union criterion-driven loss for improving 2D detection results. Besides our methodological innovations, we critically review the AP metric used in KITTI3D, which emerged as the most important dataset for comparing 3D detection results. We identify and resolve a flaw in the 11-point interpolated AP metric, affecting all previously published detection results and particularly biases the results of monocular 3D detection. We provide extensive experimental evaluations and ablation studies and set a new state-of-the-art on the KITTI3D Car class.
2019
Proceedings of the IEEE International Conference on Computer Vision
New York
Institute of Electrical and Electronics Engineers Inc.
978-1-7281-4803-8
Simonelli, A.; Bulo, S. R.; Porzi, L.; Lopez-Antequera, M.; Kontschieder, P.
Disentangling Monocular 3D Object Detection / Simonelli, A.; Bulo, S. R.; Porzi, L.; Lopez-Antequera, M.; Kontschieder, P.. - ELETTRONICO. - 2019-:(2019), pp. 1991-1999. (Intervento presentato al convegno 17th IEEE/CVF International Conference on Computer Vision, ICCV 2019 tenutosi a kor nel 2019) [10.1109/ICCV.2019.00208].
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11572/259387
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 381
  • ???jsp.display-item.citation.isi??? 303
  • OpenAlex ND
social impact