arXiv subjects

Javier Civera

Publications and source records attributed to Javier Civera.

At least 73 records · Page 4Linked to original sources

arXiv2023

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

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. On the other hand, Structure from Motion (SfM) leverages multi-view constraints to produce very accurate but sparse maps, as matching across images is typically limited by locally discriminative texture. In this work, we combine the strengths of both approaches by proposing a novel test-time refinement (TTR) method, denoted as SfM-TTR, that boosts the performance of single-view depth networks at test time using SfM multi-view cues. Specifically, and differently from the state of the art, we use sparse SfM point clouds as test-time self-supervisory signal, fine-tuning the network encoder to learn a better representation of the test scene. Our results show how the addition of SfM-TTR to several state-of-the-art self-supervised and supervised networks improves significantly their performance, outperforming previous TTR baselines mainly based on photometric multi-view consistency. The code is available at https://github.com/serizba/SfM-TTR.

cs.CV↗

arXiv2023

Graph-based Global Robot Localization Informing Situational Graphs with Architectural Graphs

In this paper, we propose a solution for legged robot localization using architectural plans. Our specific contributions towards this goal are several. Firstly, we develop a method for converting the plan of a building into what we denote as an architectural graph (A-Graph). When the robot starts moving in an environment, we assume it has no knowledge about it, and it estimates an online situational graph representation (S-Graph) of its surroundings. We develop a novel graph-to-graph matching method, in order to relate the S-Graph estimated online from the robot sensors and the A-Graph extracted from the building plans. Note the challenge in this, as the S-Graph may show a partial view of the full A-Graph, their nodes are heterogeneous and their reference frames are different. After the matching, both graphs are aligned and merged, resulting in what we denote as an informed Situational Graph (iS-Graph), with which we achieve global robot localization and exploitation of prior knowledge from the building plans. Our experiments show that our pipeline shows a higher robustness and a significantly lower pose error than several LiDAR localization baselines.

cs.RO↗

arXiv2022

RODIAN: Robustified Median

We propose a robust method for averaging numbers contaminated by a large proportion of outliers. Our method, dubbed RODIAN, is inspired by the key idea of MINPRAN [1]: We assume that the outliers are uniformly distributed within the range of the data and we search for the region that is least likely to contain outliers only. The median of the data within this region is then taken as RODIAN. Our approach can accurately estimate the true mean of data with more than 50% outliers and runs in time $O(n\log n)$. Unlike other robust techniques, it is completely deterministic and does not rely on a known inlier error bound. Our extensive evaluation shows that RODIAN is much more robust than the median and the least-median-of-squares. This result also holds in the case of non-uniform outlier distributions.

stat.ME↗

arXiv2022

Advanced Situational Graphs for Robot Navigation in Structured Indoor Environments

Mobile robots extract information from its environment to understand their current situation to enable intelligent decision making and autonomous task execution. In our previous work, we introduced the concept of Situation Graphs (S-Graphs) which combines in a single optimizable graph, the robot keyframes and the representation of the environment with geometric, semantic and topological abstractions. Although S-Graphs were built and optimized in real-time and demonstrated state-of-the-art results, they are limited to specific structured environments with specific hand-tuned dimensions of rooms and corridors. In this work, we present an advanced version of the Situational Graphs (S-Graphs+), consisting of the five layered optimizable graph that includes (1) metric layer along with the graph of free-space clusters (2) keyframe layer where the robot poses are registered (3) metric-semantic layer consisting of the extracted planar walls (4) novel rooms layer constraining the extracted planar walls (5) novel floors layer encompassing the rooms within a given floor level. S-Graphs+ demonstrates improved performance over S-Graphs efficiently extracting the room information while simultaneously improving the pose estimate of the robot, thus extending the robots situational awareness in the form of a five layered environmental model.

cs.RO↗

arXiv2022

On the Uncertain Single-View Depths in Colonoscopies

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. As the domain specificity of colonoscopies -- deformable low-texture environments with fluids, poor lighting conditions and abrupt sensor motions -- pose challenges to multi-view 3D reconstructions, single-view depth learning stands out as a promising line of research. Depth learning can be extended in a Bayesian setting, which enables continual learning, improves decision making and can be used to compute confidence intervals or quantify uncertainty for in-body measurements. In this paper, we explore for the first time Bayesian deep networks for single-view depth estimation in colonoscopies. Our specific contribution is two-fold: 1) an exhaustive analysis of scalable Bayesian networks for depth learning in different datasets, highlighting challenges and conclusions regarding synthetic-to-real domain changes and supervised vs. self-supervised methods; and 2) a novel teacher-student approach to deep depth learning that takes into account the teacher uncertainty.

cs.CV↗

arXiv2022

Situational Graphs for Robot Navigation in Structured Indoor Environments

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. 3D scene graphs are an emerging field of research that propose to represent the environment in a joint model comprising geometric, semantic and relational/topological dimensions. Although 3D scene graphs have already been combined with SLAM techniques to provide robots with situational understanding, further research is still required to effectively deploy them on-board mobile robots. To this end, we present in this paper a novel, real-time, online built Situational Graph (S-Graph), which combines in a single optimizable graph, the representation of the environment with the aforementioned three dimensions, together with the robot pose. Our method utilizes odometry readings and planar surfaces extracted from 3D LiDAR scans, to construct and optimize in real-time a three layered S-Graph that includes (1) a robot tracking layer where the robot poses are registered, (2) a metric-semantic layer with features such as planar walls and (3) our novel topological layer constraining the planar walls using higher-level features such as corridors and rooms. Our proposal does not only demonstrate state-of-the-art results for pose estimation of the robot, but also contributes with a metric-semantic-topological model of the environment

cs.RO↗

arXiv2022

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

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. Specifically, we fit the object trajectories to cumulative B-Splines curves, which allow us to interpolate, at any intermediate time stamp, not only their poses but also their linear and angular velocities and accelerations. Additionally, we derive in this work the analytical $SE(3)$ Jacobians needed by the optimization, being applicable to any other approach that uses this type of curves. To the best of our knowledge this is the first work that proposes 6-DoF continuous-time object tracking, which we endorse with significant computational cost reduction thanks to our analytical derivations. We evaluate our proposal in synthetic data and in a public benchmark, showing competitive results in localization and significant improvements in velocity estimation in comparison to discrete-time approaches.

cs.CV↗

arXiv2022

HARA: A Hierarchical Approach for Robust Rotation Averaging

We propose a novel hierarchical approach for multiple rotation averaging, dubbed HARA. Our method incrementally initializes the rotation graph based on a hierarchy of triplet support. The key idea is to build a spanning tree by prioritizing the edges with many strong triplet supports and gradually adding those with weaker and fewer supports. This reduces the risk of adding outliers in the spanning tree. As a result, we obtain a robust initial solution that enables us to filter outliers prior to nonlinear optimization. With minimal modification, our approach can also integrate the knowledge of the number of valid 2D-2D correspondences. We perform extensive evaluations on both synthetic and real datasets, demonstrating state-of-the-art results.

cs.CV↗

arXiv2022

Danish Airs and Grounds: A Dataset for Aerial-to-Street-Level Place Recognition and Localization

Place recognition and visual localization are particularly challenging in wide baseline configurations. In this paper, we contribute with the \emph{Danish Airs and Grounds} (DAG) dataset, a large collection of street-level and aerial images targeting such cases. Its main challenge lies in the extreme viewing-angle difference between query and reference images with consequent changes in illumination and perspective. The dataset is larger and more diverse than current publicly available data, including more than 50 km of road in urban, suburban and rural areas. All images are associated with accurate 6-DoF metadata that allows the benchmarking of visual localization methods. We also propose a map-to-image re-localization pipeline, that first estimates a dense 3D reconstruction from the aerial images and then matches query street-level images to street-level renderings of the 3D model. The dataset can be downloaded at: https://frederikwarburg.github.io/DAG

cs.CV↗

arXiv2022

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

In this work, we derive a model for the covariance of the visual residuals in multi-view SfM, odometry and SLAM setups. The core of our approach is the formulation of the residual covariances as a combination of geometric and photometric noise sources. And our key novel contribution is the derivation of a term modelling how local 2D patches suffer from perspective deformation when imaging 3D surfaces around a point. Together, these add up to an efficient and general formulation which not only improves the accuracy of both feature-based and direct methods, but can also be used to estimate more accurate measures of the state entropy and hence better founded point visibility thresholds. We validate our model with synthetic and real data and integrate it into photometric and feature-based Bundle Adjustment, improving their accuracy with a negligible overhead.

cs.CV↗

arXiv2021

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

Uncertainty quantification is essential for robotic perception, as overconfident or point estimators can lead to collisions and damages to the environment and the robot. In this paper, we evaluate scalable approaches to uncertainty quantification in single-view supervised depth learning, specifically MC dropout and deep ensembles. For MC dropout, in particular, we explore the effect of the dropout at different levels in the architecture. We show that adding dropout in all layers of the encoder brings better results than other variations found in the literature. This configuration performs similarly to deep ensembles with a much lower memory footprint, which is relevant forapplications. Finally, we explore the use of depth uncertainty for pseudo-RGBD ICP and demonstrate its potential to estimate accurate two-view relative motion with the real scale.

cs.CV↗

arXiv2021

Bayesian Triplet Loss: Uncertainty Quantification in Image Retrieval

Uncertainty quantification in image retrieval is crucial for downstream decisions, yet it remains a challenging and largely unexplored problem. Current methods for estimating uncertainties are poorly calibrated, computationally expensive, or based on heuristics. We present a new method that views image embeddings as stochastic features rather than deterministic features. Our two main contributions are (1) a likelihood that matches the triplet constraint and that evaluates the probability of an anchor being closer to a positive than a negative; and (2) a prior over the feature space that justifies the conventional l2 normalization. To ensure computational efficiency, we derive a variational approximation of the posterior, called the Bayesian triplet loss, that produces state-of-the-art uncertainty estimates and matches the predictive performance of current state-of-the-art methods.

cs.CV↗

arXiv2021

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

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. In this paper we present Endo-Depth-and-Motion, a pipeline that estimates the 6-degrees-of-freedom camera pose and dense 3D scene models from monocular endoscopic videos. Our approach leverages recent advances in self-supervised depth networks to generate pseudo-RGBD frames, then tracks the camera pose using photometric residuals and fuses the registered depth maps in a volumetric representation. We present an extensive experimental evaluation in the public dataset Hamlyn, showing high-quality results and comparisons against relevant baselines. We also release all models and code for future comparisons.

cs.CV↗

arXiv2021

Rotation-Only Bundle Adjustment

We propose a novel method for estimating the global rotations of the cameras independently of their positions and the scene structure. When two calibrated cameras observe five or more of the same points, their relative rotation can be recovered independently of the translation. We extend this idea to multiple views, thereby decoupling the rotation estimation from the translation and structure estimation. Our approach provides several benefits such as complete immunity to inaccurate translations and structure, and the accuracy improvement when used with rotation averaging. We perform extensive evaluations on both synthetic and real datasets, demonstrating consistent and significant gains in accuracy when used with the state-of-the-art rotation averaging method.

cs.CV↗

arXiv2020

Geometric Interpretations of the Normalized Epipolar Error

In this work, we provide geometric interpretations of the normalized epipolar error. Most notably, we show that it is directly related to the following quantities: (1) the shortest distance between the two backprojected rays, (2) the dihedral angle between the two bounding epipolar planes, and (3) the $L_1$-optimal angular reprojection error.

cs.CV↗

arXiv2020

Robust Single Rotation Averaging

We propose a novel method for single rotation averaging using the Weiszfeld algorithm. Our contribution is threefold: First, we propose a robust initialization based on the elementwise median of the input rotation matrices. Our initial solution is more accurate and robust than the commonly used chordal $L_2$-mean. Second, we propose an outlier rejection scheme that can be incorporated in the Weiszfeld algorithm to improve the robustness of $L_1$ rotation averaging. Third, we propose a method for approximating the chordal $L_1$-mean using the Weiszfeld algorithm. An extensive evaluation shows that both our method and the state of the art perform equally well with the proposed outlier rejection scheme, but ours is $2-4$ times faster.

cs.CV↗

arXiv2020

DOT: Dynamic Object Tracking for Visual SLAM

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. DOT combines instance segmentation and multi-view geometry to generate masks for dynamic objects in order to allow SLAM systems based on rigid scene models to avoid such image areas in their optimizations. To determine which objects are actually moving, DOT segments first instances of potentially dynamic objects and then, with the estimated camera motion, tracks such objects by minimizing the photometric reprojection error. This short-term tracking improves the accuracy of the segmentation with respect to other approaches. In the end, only actually dynamic masks are generated. We have evaluated DOT with ORB-SLAM 2 in three public datasets. Our results show that our approach improves significantly the accuracy and robustness of ORB-SLAM 2, especially in highly dynamic scenes.

cs.CV↗

arXiv2020

Robust Uncertainty-Aware Multiview Triangulation

We propose a robust and efficient method for multiview triangulation and uncertainty estimation. Our contribution is threefold: First, we propose an outlier rejection scheme using two-view RANSAC with the midpoint method. By prescreening the two-view samples prior to triangulation, we achieve the state-of-the-art efficiency. Second, we compare different local optimization methods for refining the initial solution and the inlier set. With an iterative update of the inlier set, we show that the optimization provides significant improvement in accuracy and robustness. Third, we model the uncertainty of a triangulated point as a function of three factors: the number of cameras, the mean reprojection error and the maximum parallax angle. Learning this model allows us to quickly interpolate the uncertainty at test time. We validate our method through an extensive evaluation.

cs.CV↗