Search Results for author: Javier Civera

Found 42 papers, 23 papers with code

Unifying Local and Global Multimodal Features for Place Recognition in Aliased and Low-Texture Environments

1 code implementation20 Mar 2024 Alberto García-Hernández, Riccardo Giubilato, Klaus H. Strobl, Javier Civera, Rudolph Triebel

Perceptual aliasing and weak textures pose significant challenges to the task of place recognition, hindering the performance of Simultaneous Localization and Mapping (SLAM) systems.

Re-Ranking Simultaneous Localization and Mapping

PCR-99: A Practical Method for Point Cloud Registration with 99% Outliers

1 code implementation26 Feb 2024 Seong Hun Lee, Javier Civera, Patrick Vandewalle

We propose a robust method for point cloud registration that can handle both unknown scales and extreme outlier ratios.

Point Cloud Registration

From Correspondences to Pose: Non-minimal Certifiably Optimal Relative Pose without Disambiguation

1 code implementation10 Dec 2023 Javier Tirado-Garín, Javier Civera

Estimating the relative camera pose from $n \geq 5$ correspondences between two calibrated views is a fundamental task in computer vision.

Pose Estimation valid

Optimal Transport Aggregation for Visual Place Recognition

1 code implementation27 Nov 2023 Sergio Izquierdo, Javier Civera

The task of Visual Place Recognition (VPR) aims to match a query image against references from an extensive database of images from different places, relying solely on visual cues.

Re-Ranking Visual Place Recognition

Motion-Bias-Free Feature-Based SLAM

1 code implementation13 Sep 2023 Alejandro Fontan, Javier Civera, Michael Milford

In this paper we show that SLAM commutativity, that is, consistency in trajectory estimates on forward and reverse traverses of the same route, is a significant issue for the state of the art.

Robust Single Rotation Averaging Revisited

1 code implementation11 Sep 2023 Seong Hun Lee, Javier Civera

In this work, we propose a novel method for robust single rotation averaging that can efficiently handle an extremely large fraction of outliers.

Faster Optimization in S-Graphs Exploiting Hierarchy

no code implementations22 Aug 2023 Hriday Bavle, Jose Luis Sanchez-Lopez, Javier Civera, Holger Voos

A global optimization of the compressed graph is performed every time a loop closure is detected.

DAC: Detector-Agnostic Spatial Covariances for Deep Local Features

1 code implementation20 May 2023 Javier Tirado-Garín, Frederik Warburg, Javier Civera

Current deep visual local feature detectors do not model the spatial uncertainty of detected features, producing suboptimal results in downstream applications.

Ray-Patch: An Efficient Querying for Light Field Transformers

1 code implementation16 May 2023 T. Berriel Martins, Javier Civera

In this paper we propose the Ray-Patch querying, a novel model to efficiently query transformers to decode implicit representations into target views.

S-Graphs+: Real-time Localization and Mapping leveraging Hierarchical Representations

1 code implementation22 Dec 2022 Hriday Bavle, Jose Luis Sanchez-Lopez, Muhammad Shaheer, Javier Civera, Holger Voos

In this paper, we present an evolved version of Situational Graphs, which jointly models in a single optimizable factor graph (1) a pose graph, as a set of robot keyframes comprising associated measurements and robot poses, and (2) a 3D scene graph, as a high-level representation of the environment that encodes its different geometric elements with semantic attributes and the relational information between them.

What's Wrong with the Absolute Trajectory Error?

1 code implementation10 Dec 2022 Seong Hun Lee, Javier Civera

This metric is an attractive alternative to the ATE, in that it is capable of discerning the varying trajectory accuracy as the inlier trajectory error or the number of outliers varies.

SfM-TTR: Using Structure from Motion for Test-Time Refinement of Single-View Depth Networks

1 code implementation CVPR 2023 Sergio Izquierdo, Javier Civera

Estimating a dense depth map from a single view is geometrically ill-posed, and state-of-the-art methods rely on learning depth's relation with visual appearance using deep neural networks.

Advanced Situational Graphs for Robot Navigation in Structured Indoor Environments

no code implementations16 Nov 2022 Hriday Bavle, Jose Luis Sanchez-Lopez, Muhammad Shaheer, Javier Civera, Holger Voos

Mobile robots extract information from its environment to understand their current situation to enable intelligent decision making and autonomous task execution.

Decision Making Robot Navigation

Situational Graphs for Robot Navigation in Structured Indoor Environments

no code implementations24 Feb 2022 Hriday Bavle, Jose Luis Sanchez-Lopez, Muhammad Shaheer, Javier Civera, Holger Voos

Mobile robots should be aware of their situation, comprising the deep understanding of their surrounding environment along with the estimation of its own state, to successfully make intelligent decisions and execute tasks autonomously in real environments.

Pose Estimation Robot Navigation

A Model for Multi-View Residual Covariances based on Perspective Deformation

no code implementations1 Feb 2022 Alejandro Fontan, Laura Oliva, Javier Civera, Rudolph Triebel

In this work, we derive a model for the covariance of the visual residuals in multi-view SfM, odometry and SLAM setups.

Jacobian Computation for Cumulative B-Splines on SE(3) and Application to Continuous-Time Object Tracking

no code implementations25 Jan 2022 Javier Tirado, Javier Civera

In this paper we propose a method that estimates the $SE(3)$ continuous trajectories (orientation and translation) of the dynamic rigid objects present in a scene, from multiple RGB-D views.

Object Tracking Translation

On the Uncertain Single-View Depths in Colonoscopies

no code implementations16 Dec 2021 Javier Rodríguez-Puigvert, David Recasens, Javier Civera, Rubén Martínez-Cantín

Estimating depth information from endoscopic images is a prerequisite for a wide set of AI-assisted technologies, such as accurate localization and measurement of tumors, or identification of non-inspected areas.

Continual Learning Decision Making +2

HARA: A Hierarchical Approach for Robust Rotation Averaging

1 code implementation CVPR 2022 Seong Hun Lee, Javier Civera

We propose a novel hierarchical approach for multiple rotation averaging, dubbed HARA.


Bayesian Deep Neural Networks for Supervised Learning of Single-View Depth

no code implementations29 Apr 2021 Javier Rodríguez-Puigvert, Rubén Martínez-Cantín, Javier Civera

In this paper, we evaluate scalable approaches to uncertainty quantification in single-view supervised depth learning, specifically MC dropout and deep ensembles.

Uncertainty Quantification

Endo-Depth-and-Motion: Reconstruction and Tracking in Endoscopic Videos using Depth Networks and Photometric Constraints

1 code implementation30 Mar 2021 David Recasens, José Lamarca, José M. Fácil, J. M. M. Montiel, Javier Civera

Estimating a scene reconstruction and the camera motion from in-body videos is challenging due to several factors, e. g. the deformation of in-body cavities or the lack of texture.

Bayesian Triplet Loss: Uncertainty Quantification in Image Retrieval

no code implementations ICCV 2021 Frederik Warburg, Martin Jørgensen, Javier Civera, Søren Hauberg

Uncertainty quantification in image retrieval is crucial for downstream decisions, yet it remains a challenging and largely unexplored problem.

Computational Efficiency Image Retrieval +2

Rotation-Only Bundle Adjustment

no code implementations CVPR 2021 Seong Hun Lee, Javier Civera

We propose a novel method for estimating the global rotations of the cameras independently of their positions and the scene structure.


DOT: Dynamic Object Tracking for Visual SLAM

no code implementations30 Sep 2020 Irene Ballester, Alejandro Fontan, Javier Civera, Klaus H. Strobl, Rudolph Triebel

In this paper we present DOT (Dynamic Object Tracking), a front-end that added to existing SLAM systems can significantly improve their robustness and accuracy in highly dynamic environments.

Instance Segmentation Object +3

Robust Uncertainty-Aware Multiview Triangulation

1 code implementation4 Aug 2020 Seong Hun Lee, Javier Civera

We propose a robust and efficient method for multiview triangulation and uncertainty estimation.

Geometric Interpretations of the Normalized Epipolar Error

no code implementations4 Aug 2020 Seong Hun Lee, Javier Civera

In this work, we provide geometric interpretations of the normalized epipolar error.

Robust Single Rotation Averaging

1 code implementation1 Apr 2020 Seong Hun Lee, Javier Civera

We propose a novel method for single rotation averaging using the Weiszfeld algorithm.

RGB-D Odometry and SLAM

no code implementations19 Jan 2020 Javier Civera, Seong Hun Lee

The two topics are closely related, as the former aims to track the incremental camera motion with respect to a local map of the scene, and the latter to jointly estimate the camera trajectory and the global map with consistency.

3D Scene Reconstruction Navigate +2

Triangulation: Why Optimize?

no code implementations27 Jul 2019 Seong Hun Lee, Javier Civera

We propose a novel alternative to the classic midpoint method that leads to significantly lower 2D errors and parallax errors.

CAM-Convs: Camera-Aware Multi-Scale Convolutions for Single-View Depth

1 code implementation CVPR 2019 Jose M. Facil, Benjamin Ummenhofer, Huizhong Zhou, Luis Montesano, Thomas Brox, Javier Civera

Single-view depth estimation suffers from the problem that a network trained on images from one camera does not generalize to images taken with a different camera model.

3D Depth Estimation Depth Prediction +1

Closed-Form Optimal Two-View Triangulation Based on Angular Errors

no code implementations ICCV 2019 Seong Hun Lee, Javier Civera

In this paper, we study closed-form optimal solutions to two-view triangulation with known internal calibration and pose.

Vocal Bursts Valence Prediction

Condition-Invariant Multi-View Place Recognition

no code implementations25 Feb 2019 Jose M. Facil, Daniel Olid, Luis Montesano, Javier Civera

Visual place recognition is particularly challenging when places suffer changes in its appearance.

Visual Place Recognition

Single-View Place Recognition under Seasonal Changes

1 code implementation20 Aug 2018 Daniel Olid, José M. Fácil, Javier Civera

First we pre-process and propose a partition for the Nordland dataset, frequently used for place recognition research without consensus on the partitions.

Autonomous Navigation

Loosely-Coupled Semi-Direct Monocular SLAM

1 code implementation26 Jul 2018 Seong Hun Lee, Javier Civera

We propose a novel semi-direct approach for monocular simultaneous localization and mapping (SLAM) that combines the complementary strengths of direct and feature-based methods.

Simultaneous Localization and Mapping

DynaSLAM: Tracking, Mapping and Inpainting in Dynamic Scenes

6 code implementations14 Jun 2018 Berta Bescos, José M. Fácil, Javier Civera, José Neira

And it also estimates a map of the static parts of the scene, which is a must for long-term applications in real-world environments.

Autonomous Vehicles object-detection +1

RGBDTAM: A Cost-Effective and Accurate RGB-D Tracking and Mapping System

1 code implementation2 Mar 2017 Alejo Concha, Javier Civera

Simultaneous Localization and Mapping using RGB-D cameras has been a fertile research topic in the latest decade, due to the suitability of such sensors for indoor robotics.


Single-View and Multi-View Depth Fusion

no code implementations22 Nov 2016 José M. Fácil, Alejo Concha, Luis Montesano, Javier Civera

The single and multi-view fusion we propose is challenging in several aspects.

Depth Estimation

Cannot find the paper you are looking for? You can Submit a new open access paper.