Renato Martins

I am a PhD student on robotics and computer vision at Inria Sophia Antipolis under supervision of Dr. Patrick Rives, working towards a degree from the Ecole des Mines de Paris. My thesis is about the design of robust/efficient direct image registration and 3D mapping using wide field of view cameras (panoramic and spherical images) and its applications to mobile robotics.

I hold a Bachelor's degree in Control and Automation Engineering (2011) from the University of Campinas and Master's degrees in Electrical Engineering (2013) from the University of Campinas and in Computer Science from the TU Compiegne (where I did an internship in 2008/2009 during my undergraduate studies). During my masters, I was also affiliated with the Robotics and Vision Lab at CTI Renato Archer research center.

CV  /  My Inria webpage  /  MSc Thesis  /  Google Scholar  /  LinkedIn  /  Email

Research

My domains of interest are on computer vision and robotics perception, more specifically in direct image registration, visual odometry, visual SLAM and 3D mapping using RGB-D cameras.

An Efficient Rotation and Translation Decoupled Initialization from Large Field of View Depth Images
Renato Martins, Eduardo Fernandez Moral and Patrick Rives
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2017
talk slides / bibtex

This paper describes a registration technique using the normal vectors of depth images. The technique is computed in a decoupled and non-iterative way, and with a large convergence domain. This formulation can be used with an initialization framework to improve the convergence of direct registration methods.


A New Metric for Evaluating Semantic Segmentation: Leveraging Global and Contour Accuracy
Eduardo Fernandez-Moral, Renato Martins, Denis Wolf and Patrick Rives
IEEE/RSJ International Conference on Intelligent Robots and Systems Workshop on Planning, Perception and Navigation for Intelligent Vehicles (IROS PPNIV), 2017
talk slides / bibtex

In this paper, we propose a new metric to evaluate semantic segmentation. This new metric accounts for both global and contour accuracy in a simple formulation to overcome the weaknesses of the most commonly used metrics.

Adaptive Direct RGB-D Registration and Mapping for Large Motions
Renato Martins, Eduardo Fernandez Moral and Patrick Rives
Asian Conference on Computer Vision (ACCV) , 2016
poster / bibtex

This work addresses the challenging cases of large motions in direct image registration. We explore the complementary aspects of a classical direct VO and direct point-to-plane strategies, in terms of convergence, by using a modified cost function, where the geometric term prevails in the first coarse iterations, while the intensity data term dominates in the finer increments.


Increasing the Convergence Domain of RGB-D Direct Registration Methods for Vision-based Localization in Large Scale Environments
Renato Martins, Patrick Rives
IEEE Intelligent Transportation Systems Conference Workshop on Planning, Perception and Navigation for Intelligent Vehicles (ITSC PPNIV), 2016
talk slides / bibtex

In this paper, we show the outcome of a more stable and robust direct registration task in the density/sparsity of the representation (the number of keyframes) in outdoor scene mapping. This allows storing a sparser local representation whilst maintaining a topological structure at large-scale that is accurate enough to ensure the convergence of a task in the neighbourhood of the scene model.

Dense Accurate Urban Mapping from Spherical RGB-D Images
Renato Martins, Eduardo Fernandez Moral, Patrick Rives
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2015
talk slides / bibtex

This work is about exploiting jointly intensity and depth information to generate more precise keyframes for visual odometry or image rendering. The main core of the paper is a depth regularization that considers both geometric and photometric image constraints (planar and superpixel segmentation).

A Compact Spherical RGBD Keyframe-based Representation
Tawsif Gokhool, Renato Martins, Patrick Rives, Noela Despre
IEEE International Conference on Robotics and Automation (ICRA) , 2015
highlight talk / poster / bibtex

We proposed in this paper an ego-centric spherical representation to efficiently store a full RGB-D model of a 3D environment. For that, we used the notions of "keyframe" to select the most informative frames, along with the propation/correction of the depth image by representing the uncertainties of the geometry and the pose.

Teaching
teach

Fall 2015: Numerical Analysis (Analyse numérique I, MAM3)
Engineering students (3rd year) from Polytech'Nice.
Teacher assistant of Dr. Holger Heumann.

Spring 2016: Computer Systems (Systèmes informatiques, SY27)
Bachelor students (1st year) from Université de Nice.
Teacher assistant of Pr. Sid Touati.


Template of this webpage.

shopify analytics