AIConfPaper
← Search

Vincent Gaudillière

6 accepted papers

2026

Cov2Pose: Leveraging Spatial Covariance for Direct Manifold-aware 6-DoF Object Pose Estimation

Nassim Ali Ousalah, Peyman Rostami, Vincent Gaudillière, Emmanuel Koumandakis, Anis Kacem, Enjie Ghorbel +1
CVPR 2026

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,

Cited by 0Source ↗Scholar ↗
2025

Hybrid Attention for Robust RGB-T Pedestrian Detection in Real-World Conditions

Arunkumar Rathinam, Leo Pauly, Abd El Rahman Shabayek, Wassim Rharbaoui, Anis Kacem, Vincent Gaudillière +1
RA-L 2025

Multispectral pedestrian detection has gained significant attention in recent years, particularly in autonomous driving applications. To address the challenges posed by adversarial illumination conditions, the combination of thermal and visible images has demonstrated its advantages. However, existi

Cited by 2Source ↗Scholar ↗
2023

3D-Aware Object Localization using Gaussian Implicit Occupancy Function

Vincent Gaudillière, Leo Pauly, Arunkumar Rathinam, Albert Garcia Sanchez, Mohamed Adel Musallam, Djamila Aouada
IROS 2023poster

To automatically localize a target object in an image is crucial for many computer vision applications. To represent the 2D object, ellipse labels have recently been identified as a promising alternative to axis-aligned bounding boxes. This paper further considers 3D-aware ellipse labels, i.e., elli…

Cited by 5Source ↗Scholar ↗
2022

Leveraging Equivariant Features for Absolute Pose Regression

Mohamed Adel Musallam, Vincent Gaudillière, Miguel Ortiz del Castillo, Kassem Al Ismaeil, Djamila Aouada
CVPR 2022poster

While end-to-end approaches have achieved state-of-the-art performance in many perception tasks, they are not yet able to compete with 3D geometry-based methods in pose estimation. Moreover, absolute pose regression has been shown to be more related to image retrieval. As a result, we hypothesize th…

Cited by 35PDF ↗Scholar ↗
2020

Perspective-2-Ellipsoid: Bridging the Gap Between Object Detections and 6-DoF Camera Pose

Vincent Gaudillière, Gilles Simon, Marie-Odile Berger
RA-L 2020

Recent years have seen the emergence of very effective ConvNet-based object detectors that have reconfigured the computer vision landscape. As a consequence, new approaches that propose object-based reasoning to solve traditional problems, such as camera pose estimation, have appeared. In particular

Cited by 18Source ↗Scholar ↗