Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Ousalah, Nassim Ali, Rostami, Peyman, Gaudillière, Vincent, Koumandakis, Emmanuel, Kacem, Anis, Ghorbel, Enjie, Aouada, Djamila
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2603.19961
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866908915454705664
author Ousalah, Nassim Ali
Rostami, Peyman
Gaudillière, Vincent
Koumandakis, Emmanuel
Kacem, Anis
Ghorbel, Enjie
Aouada, Djamila
author_facet Ousalah, Nassim Ali
Rostami, Peyman
Gaudillière, Vincent
Koumandakis, Emmanuel
Kacem, Anis
Ghorbel, Enjie
Aouada, Djamila
contents In this paper, we address the problem of 6-DoF object pose estimation from a single RGB image. Indirect methods that typically predict intermediate 2D keypoints, followed by a Perspective-n-Point solver, have shown great performance. Direct approaches, which regress the pose in an end-to-end manner, are usually computationally more efficient but less accurate. However, direct pose regression heads rely on globally pooled features, ignoring spatial second-order statistics despite their informativeness in pose prediction. They also predict, in most cases, discontinuous pose representations that lack robustness. Herein, we therefore propose a covariance-pooled representation that encodes convolutional feature distributions as a symmetric positive definite (SPD) matrix. Moreover, we propose a novel pose encoding in the form of an SPD matrix via its Cholesky decomposition. Pose is then regressed in an end-to-end manner with a manifold-aware network head, taking into account the Riemannian geometry of SPD matrices. Experiments and ablations consistently demonstrate the relevance of second-order pooling and continuous representations for direct pose regression, including under partial occlusion.
format Preprint
id arxiv_https___arxiv_org_abs_2603_19961
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Cov2Pose: Leveraging Spatial Covariance for Direct Manifold-aware 6-DoF Object Pose Estimation
Ousalah, Nassim Ali
Rostami, Peyman
Gaudillière, Vincent
Koumandakis, Emmanuel
Kacem, Anis
Ghorbel, Enjie
Aouada, Djamila
Computer Vision and Pattern Recognition
In this paper, we address the problem of 6-DoF object pose estimation from a single RGB image. Indirect methods that typically predict intermediate 2D keypoints, followed by a Perspective-n-Point solver, have shown great performance. Direct approaches, which regress the pose in an end-to-end manner, are usually computationally more efficient but less accurate. However, direct pose regression heads rely on globally pooled features, ignoring spatial second-order statistics despite their informativeness in pose prediction. They also predict, in most cases, discontinuous pose representations that lack robustness. Herein, we therefore propose a covariance-pooled representation that encodes convolutional feature distributions as a symmetric positive definite (SPD) matrix. Moreover, we propose a novel pose encoding in the form of an SPD matrix via its Cholesky decomposition. Pose is then regressed in an end-to-end manner with a manifold-aware network head, taking into account the Riemannian geometry of SPD matrices. Experiments and ablations consistently demonstrate the relevance of second-order pooling and continuous representations for direct pose regression, including under partial occlusion.
title Cov2Pose: Leveraging Spatial Covariance for Direct Manifold-aware 6-DoF Object Pose Estimation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2603.19961