Renato Martins

I am an Associate Professor (Maître de Conférences) in the Université de Bourgogne, Le Creusot/France, working in the "Vision for Robotics" - VIBOT team of the "Artifical Imagery and Vision" - ImViA Lab.

Previously, I did my PhD at INRIA Sophia Antipolis/France and at Ecole des Mines de Paris / Université Paris Sciences et Lettres, where I was advised by Dr. Patrick Rives. Then, I was a post-doctoral researcher in the CNRS I3S laboratory, in the ACENTAURI / CHORALE group at INRIA and with the VeRLab laboratory at Universidade Federal de Minas Gerais/Brazil, with whom I maintain tight research collaborations.

My research interests lie in Computer Vision, Machine Learning and Robot Vision, more specifically in the topics of 3D vision, geometric deep learning, human motion analysis, video prediction, and RGB-D image analysis and processing (perspective, omnidirectional).

Publications  /  Collaborators  /  Software  /  Google Scholar  /  Contact

     
News
  • [NEW] 02.08.2022: RAL paper accepted: "Calibration for polarimetric cameras" [arXiv]
  • [NEW] 05.03.2022: Our paper on "Learning Geodesic-Aware Local Features from RGB-D Images" is accepted in the journal CVIU [arXiv]
  • [NEW] 02.01.2022: WACV 2022 paper accepted: "Creating and Reenacting Controllable 3D Humans with Differentiable Rendering" [arXiv]
  • 12.11.2021: Outstanding Reviewer of 3DV 2021
  • 23.10.2021: Co-advisor of the best Brazilian M.Sc. Thesis on Computer Vision and Image Processing at SIBGRAPI 2021. Congrats Joao Ferreira!
  • 28.09.2021: NeurIPS 2021 paper accepted: "Extracting Deformation-Aware Local Features by Learning to Deform" [arXiv]
  • 01.09.2021: I joined as Associate Professor (Maître de Conférences) the VIsion for RoBOTics - VIBOT / ImViA Lab at the Université de Bourgogne
Community Service & Reviewing Activities
Recent Papers

A Practical Calibration Method for RGB Micro-Grid Polarimetric Cameras
Joaquin Rodriguez, Lew Lew-Yan-Voon, Renato Martins, and Olivier Morel
Robotics and Automation Letters (RAL), 2022
arXiv / project webpage / bibtex / github code

This paper proposes a calibration strategy to estimate the parameters of a polarization camera and lens, i.e., to construct the super-pixel matrix with the four filters' orientations with minimal controlled conditions. The calibration only requires few samples of a uniform and linearly polarized light.

Learning Geodesic-Aware Local Features from RGB-D Images
Guilherme Potje, Renato Martins, Felipe Cadar, and Erickson R. Nascimento
Computer Vision and Image Understanding (CVIU), 2022
arXiv / project webpage / bibtex / github code

In this paper, we present two complementary local descriptors strategies to compute geodesic-aware features efficiently: one efficient binary descriptor based on handcrafted binary tests (named GeoBit), and one learning-based descriptor (GeoPatch) with a convolutional neural networks (CNNs) to extract visual features.


Template of this webpage.