COMPORT , Andrew I.

Neural scene representations, such as Neural Radiance Fields (NeRF), are based on training a multilayer perceptron (MLP) using a set of color images with known poses. An increasing number of devices now produce RGB-D(color + depth) information, which has been shown to be very important for a wide range of tasks. Therefore, the aim of this paper...

This paper describes a dense tracking system (both monocular and multi-camera) which each perform in real-time (45Hz). The proposed approach combines a prior dense photometric model with online visual odometry which enables handling dynamic changes in the scene. In particular it will be shown how the technique takes into account large...

résumé

Learning a 3D representation of a scene has been a challenging problem for decades in computer vision. Recent advances in implicit neural representation from images using neural radiance fields(NeRF) have shown promising results. Some of the limitations of previous NeRF based methods include longer training time, and inaccurate underlying...

In this paper a dense structure model is developed for stereo image based Simultaneous Localization And Mapping (SLAM). It is proposed to model dense environment structure incrementally by robustly integrating disparity maps from current and previous time instants. In this way disparities can be refined over time to favor consistent 3D...

Abstract

In this paper a dense structure model is developed for stereo image based Simultaneous Localization And Mapping (SLAM). It is proposed to model dense environment structure incrementally by robustly integrating disparity maps from current and previous time instants. In this way disparities can be refined over time to favor consistent 3D...

no abstract

This paper proposes a new visual SLAM technique that not only integrates 6 degrees of freedom (DOF) pose and dense structure but also simultaneously integrates the colour information contained in the images over time. This involves developing an inverse model for creating a super-resolution map from many low resolution images. Contrary to...

This paper proposes a new visual SLAM technique that not only integrates 6DOF pose and dense structure but also simultaneously integrates the color information contained in the images over time. This involves developing an inverse model for creating a super-resolution map from many low resolution images. Contrary to classic super-resolution...

Abstract

This paper proposes an approach to real-time dense localisation and mapping that aims at unifying two different representations commonly used to define dense models. On one hand, much research has looked at 3D dense model representations using voxel grids in 3D. On the other hand, image-based key-frame representations for dense environment...

This paper introduces a novel color tracking model for image registration that exploits directly the color information provided by standard color cameras. Furthermore, unlike previous approaches, the color tracking model is designed to handle both global and local illumination changes within a robust framework that also rejects outliers such as...

Abstract

no abstract

Acquiring High Dynamic Range (HDR) photos from several images, with an active shutter providing different exposures (sensor integration periods), has been widely commercialised in photography for static camera positions. In the case of a mobile video sensor (as is the case in robotics), this problem is more difficult due to real-time motion of...

— Acquiring High Dynamic Range (HDR) photos from several images, with an active shutter providing different exposures (sensor integration periods), has been widely commercialised in photography for static camera positions. In the case of a mobile video sensor (as is the case in robotics), this problem is more difficult due to real-time motion...

The objective of this article is to provide a generalized framework of a novel method that investigates the problem of combining and fusing different types of measurements for pose estimation. The proposed method allows to jointly minimize the different metric errors as a single measurement vector in n-dimensions without requiring a scaling...

RGB-D view registration has been widely studied by the robotics and computer vision community. The well known Iterative Closest Points (ICP) method and its variants prevail for estimating the relative pose between sensors. However , the optimization is performed locally and by consequence it can get trapped in local minima. Global registration...

International audience

This paper proposes a model for large illumination variations to improve direct 3D tracking techniques since they are highly prone to illumination changes. Within this context dense monocular and multi-camera tracking techniques are presented which each perform in real-time (45Hz). The proposed approach exploits the relative advantages of both...

This paper describes a generic method for vision-based navigation in real urban environments. The proposed approach relies on a representation of the scene based on spherical images augmented with depth information and a spherical saliency map, both constructed in a learning phase. Saliency maps are built by analyzing useful information of...

In RGB-D sensor based visual odometry the goal is to estimate a sequence of camera movements using image and/or range measurements. Direct methods solve the problem by minimizing intensity error. In this work a depth map obtained from a RGB-D sensor is considered as a new measurement which is combined with a direct photometric cost function....

This paper presents methods for performing real-time semantic SLAM aimed at autonomous navigation and control of a humanoid robot in a manufacturing scenario. A novel multi-keyframe approach is proposed that simultaneously minimizes a semantic cost based on class-level features in addition to common photometric and geometric costs. The approach...

This paper proposes a novel approach called Semantic Visual Odometry (SemVO) which incorporates class-level consistency priors into the problem of 6-DoF Visual Odometry. Dense class-level labels are learnt for each pixel of the image using a CNN trained for semantic segmentation. A semantic error is formulated penalising the sum of squared...