Javier Civera

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. 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.

Pablo Azagra, Carlos Sostres, Ángel Ferrandez et al.

Computer-assisted systems are becoming broadly used in medicine. In endoscopy, most research focuses on the automatic detection of polyps or other pathologies, but localization and navigation of the endoscope are completely performed manually by physicians. To broaden this research and bring spatial Artificial Intelligence to endoscopies, data from complete procedures is needed. This paper introduces the Endomapper dataset, the first collection of complete endoscopy sequences acquired during regular medical practice, making secondary use of medical data. Its main purpose is to facilitate the development and evaluation of Visual Simultaneous Localization and Mapping (VSLAM) methods in real endoscopy data. The dataset contains more than 24 hours of video. It is the first endoscopic dataset that includes endoscope calibration as well as the original calibration videos. Meta-data and annotations associated with the dataset vary from the anatomical landmarks, procedure labeling, segmentations, reconstructions, simulated sequences with ground truth and same patient procedures. The software used in this paper is publicly available.

Iacopo Catalano, Eduardo Montijano, Javier Civera et al.

Autonomous navigation in dynamic environments requires spatial representations that capture both semantic structure and temporal evolution. 3D Scene Graphs (3DSGs) provide hierarchical multi-resolution abstractions that encode geometry and semantics, but existing extensions toward dynamics largely focus on individual objects or agents. In parallel, Maps of Dynamics (MoDs) model typical motion patterns and temporal regularities, yet are usually tied to grid-based discretizations that lack semantic awareness and do not scale well to large environments. In this paper we introduce Aion, a framework that embeds temporal flow dynamics directly within a hierarchical 3DSG, effectively incorporating the temporal dimension. Aion employs a graph-based sparse MoD representation to capture motion flows over arbitrary time intervals and attaches them to navigational nodes in the scene graph, yielding more interpretable and scalable predictions that improve planning and interaction in complex dynamic environments. We provide the code at https://github.com/IacopomC/aion

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. State-of-the-art pipelines focus on the aggregation of features extracted from a deep backbone, in order to form a global descriptor for each image. In this context, we introduce SALAD (Sinkhorn Algorithm for Locally Aggregated Descriptors), which reformulates NetVLAD's soft-assignment of local features to clusters as an optimal transport problem. In SALAD, we consider both feature-to-cluster and cluster-to-feature relations and we also introduce a 'dustbin' cluster, designed to selectively discard features deemed non-informative, enhancing the overall descriptor quality. Additionally, we leverage and fine-tune DINOv2 as a backbone, which provides enhanced description power for the local features, and dramatically reduces the required training time. As a result, our single-stage method not only surpasses single-stage baselines in public VPR datasets, but also surpasses two-stage methods that add a re-ranking with significantly higher cost. Code and models are available at https://github.com/serizba/salad.

David Recasens, Martin R. Oswald, Marc Pollefeys et al.

Estimating camera motion in deformable scenes poses a complex and open research challenge. Most existing non-rigid structure from motion techniques assume to observe also static scene parts besides deforming scene parts in order to establish an anchoring reference. However, this assumption does not hold true in certain relevant application cases such as endoscopies. Deformable odometry and SLAM pipelines, which tackle the most challenging scenario of exploratory trajectories, suffer from a lack of robustness and proper quantitative evaluation methodologies. To tackle this issue with a common benchmark, we introduce the Drunkard's Dataset, a challenging collection of synthetic data targeting visual navigation and reconstruction in deformable environments. This dataset is the first large set of exploratory camera trajectories with ground truth inside 3D scenes where every surface exhibits non-rigid deformations over time. Simulations in realistic 3D buildings lets us obtain a vast amount of data and ground truth labels, including camera poses, RGB images and depth, optical flow and normal maps at high resolution and quality. We further present a novel deformable odometry method, dubbed the Drunkard's Odometry, which decomposes optical flow estimates into rigid-body camera motion and non-rigid scene deformations. In order to validate our data, our work contains an evaluation of several baselines as well as a novel tracking error metric which does not require ground truth data. Dataset and code: https://davidrecasens.github.io/TheDrunkard'sOdometry/

Hriday Bavle, Jose Luis Sanchez-Lopez, Muhammad Shaheer et al.

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. Specifically, our S-Graphs+ is a novel four-layered factor graph that includes: (1) a keyframes layer with robot pose estimates, (2) a walls layer representing wall surfaces, (3) a rooms layer encompassing sets of wall planes, and (4) a floors layer gathering the rooms within a given floor level. The above graph is optimized in real-time to obtain a robust and accurate estimate of the robots pose and its map, simultaneously constructing and leveraging high-level information of the environment. To extract this high-level information, we present novel room and floor segmentation algorithms utilizing the mapped wall planes and free-space clusters. We tested S-Graphs+ on multiple datasets, including simulated and real data of indoor environments from varying construction sites, and on a real public dataset of several indoor office areas. On average over our datasets, S-Graphs+ outperforms the accuracy of the second-best method by a margin of 10.67%, while extending the robot situational awareness by a richer scene model. Moreover, we make the software available as a docker file.

Javier Rodríguez-Puigvert, Víctor M. Batlle, J. M. M. Montiel et al.

Single-view depth estimation can be remarkably effective if there is enough ground-truth depth data for supervised training. However, there are scenarios, especially in medicine in the case of endoscopies, where such data cannot be obtained. In such cases, multi-view self-supervision and synthetic-to-real transfer serve as alternative approaches, however, with a considerable performance reduction in comparison to supervised case. Instead, we propose a single-view self-supervised method that achieves a performance similar to the supervised case. In some medical devices, such as endoscopes, the camera and light sources are co-located at a small distance from the target surfaces. Thus, we can exploit that, for any given albedo and surface orientation, pixel brightness is inversely proportional to the square of the distance to the surface, providing a strong single-view self-supervisory signal. In our experiments, our self-supervised models deliver accuracies comparable to those of fully supervised ones, while being applicable without depth ground-truth data.

Muhammad Shaheer, Jose Andres Millan-Romera, Hriday Bavle et al.

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.

Iacopo Catalano, Francesco Verdoja, Javier Civera et al.

3D Scene Graphs (3DSGs) provide hierarchical, multi-resolution abstractions that encode the geometric and semantic structure of an environment, yet their treatment of dynamics remains limited to tracking individual agents. Maps of Dynamics (MoDs) complement this by modeling aggregate motion patterns, but rely on uniform grid discretizations that lack semantic grounding and scale poorly. We present Rheos, a framework that explicitly embeds continuous directional motion models into an additional dynamics layer of a hierarchical 3DSG that enhances the navigational properties of the graph. Each dynamics node maintains a semi-wrapped Gaussian mixture model that captures multimodal directional flow as a principled probability distribution with explicit uncertainty, replacing the discrete histograms used in prior work. To enable online operation, Rheos employs reservoir sampling for bounded-memory observation buffers, parallel per-cell model updates and a principled Bayesian Information Criterion (BIC) sweep that selects the optimal number of mixture components, reducing per-update initialization cost from quadratic to linear in the number of samples. Evaluated across four spatial resolutions in a simulated pedestrian environment, Rheos consistently outperforms the discrete baseline under continuous as well as unfavorable discrete metrics. We release our implementation as open source.

Sergio Izquierdo, Javier Civera

Visual Place Recognition (VPR) plays a critical role in many localization and mapping pipelines. It consists of retrieving the closest sample to a query image, in a certain embedding space, from a database of geotagged references. The image embedding is learned to effectively describe a place despite variations in visual appearance, viewpoint, and geometric changes. In this work, we formulate how limitations in the Geographic Distance Sensitivity of current VPR embeddings result in a high probability of incorrectly sorting the top-k retrievals, negatively impacting the recall. In order to address this issue in single-stage VPR, we propose a novel mining strategy, CliqueMining, that selects positive and negative examples by sampling cliques from a graph of visually similar images. Our approach boosts the sensitivity of VPR embeddings at small distance ranges, significantly improving the state of the art on relevant benchmarks. In particular, we raise recall@1 from 75% to 82% in MSLS Challenge, and from 76% to 90% in Nordland. Models and code are available at https://github.com/serizba/cliquemining.

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. Our approach is to minimize the total truncated least unsquared deviations (TLUD) cost of geodesic distances. The proposed algorithm consists of three steps: First, we consider each input rotation as a potential initial solution and choose the one that yields the least sum of truncated chordal deviations. Next, we obtain the inlier set using the initial solution and compute its chordal $L_2$-mean. Finally, starting from this estimate, we iteratively compute the geodesic $L_1$-mean of the inliers using the Weiszfeld algorithm on $SO(3)$. An extensive evaluation shows that our method is robust against up to 99% outliers given a sufficient number of accurate inliers, outperforming the current state of the art.

Seong Hun Lee, Javier Civera

One of the limitations of the commonly used Absolute Trajectory Error (ATE) is that it is highly sensitive to outliers. As a result, in the presence of just a few outliers, it often fails to reflect the varying accuracy as the inlier trajectory error or the number of outliers varies. In this work, we propose an alternative error metric for evaluating the accuracy of the reconstructed camera trajectory. Our metric, named Discernible Trajectory Error (DTE), is computed in five steps: (1) Shift the ground-truth and estimated trajectories such that both of their geometric medians are located at the origin. (2) Rotate the estimated trajectory such that it minimizes the sum of geodesic distances between the corresponding camera orientations. (3) Scale the estimated trajectory such that the median distance of the cameras to their geometric median is the same as that of the ground truth. (4) Compute, winsorize and normalize the distances between the corresponding cameras. (5) Obtain the DTE by taking the average of the mean and the root-mean-square (RMS) of the resulting distances. 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. Using the similar idea, we also propose a novel rotation error metric, named Discernible Rotation Error (DRE), which has similar advantages to the DTE. Furthermore, we propose a simple yet effective method for calibrating the camera-to-marker rotation, which is needed for the computation of our metrics. Our methods are verified through extensive simulations.

Hriday Bavle, Jose Luis Sanchez-Lopez, Muhammad Shaheer et al.

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.

Tianchen Deng, Yue Pan, Shenghai Yuan et al.

In this paper, we provide a comprehensive overview of existing scene representation methods for robotics, covering traditional representations such as point clouds, voxels, signed distance functions (SDF), and scene graphs, as well as more recent neural representations like Neural Radiance Fields (NeRF), 3D Gaussian Splatting (3DGS), and the emerging Foundation Models. While current SLAM and localization systems predominantly rely on sparse representations like point clouds and voxels, dense scene representations are expected to play a critical role in downstream tasks such as navigation and obstacle avoidance. Moreover, neural representations such as NeRF, 3DGS, and foundation models are well-suited for integrating high-level semantic features and language-based priors, enabling more comprehensive 3D scene understanding and embodied intelligence. In this paper, we categorized the core modules of robotics into five parts (Perception, Mapping, Localization, Navigation, Manipulation). We start by presenting the standard formulation of different scene representation methods and comparing the advantages and disadvantages of scene representation across different modules. This survey is centered around the question: What is the best 3D scene representation for robotics? We then discuss the future development trends of 3D scene representations, with a particular focus on how the 3D Foundation Model could replace current methods as the unified solution for future robotic applications. The remaining challenges in fully realizing this model are also explored. We aim to offer a valuable resource for both newcomers and experienced researchers to explore the future of 3D scene representations and their application in robotics. We have published an open-source project on GitHub and will continue to add new works and technologies to this project.

Tianchen Deng, Xun Chen, Ziming Li et al.

Visual Place Recognition (VPR) has been traditionally formulated as a single-image retrieval task. Using multiple views offers clear advantages, yet this setting remains relatively underexplored and existing methods often struggle to generalize across diverse environments. In this work we introduce UniPR-3D, the first VPR architecture that effectively integrates information from multiple views. UniPR-3D builds on a VGGT backbone capable of encoding multi-view 3D representations, which we adapt by designing feature aggregators and fine-tune for the place recognition task. To construct our descriptor, we jointly leverage the 3D tokens and intermediate 2D tokens produced by VGGT. Based on their distinct characteristics, we design dedicated aggregation modules for 2D and 3D features, allowing our descriptor to capture fine-grained texture cues while also reasoning across viewpoints. To further enhance generalization, we incorporate both single- and multi-frame aggregation schemes, along with a variable-length sequence retrieval strategy. Our experiments show that UniPR-3D sets a new state of the art, outperforming both single- and multi-view baselines and highlighting the effectiveness of geometry-grounded tokens for VPR. Our code and models will be made publicly available on Github https://github.com/dtc111111/UniPR-3D.

Alejandro Fontan, Javier Civera, Michael Milford

For SLAM to be safely deployed in unstructured real world environments, it must possess several key properties that are not encompassed by conventional benchmarks. 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. Current pipelines show a significant bias between forward and reverse directions of travel, that is in addition inconsistent regarding which direction of travel exhibits better performance. In this paper we propose several contributions to feature-based SLAM pipelines that remedies the motion bias problem. In a comprehensive evaluation across four datasets, we show that our contributions implemented in ORB-SLAM2 substantially reduce the bias between forward and backward motion and additionally improve the aggregated trajectory error. Removing the SLAM motion bias has significant relevance for the wide range of robotics and computer vision applications where performance consistency is important.

Hriday Bavle, Jose Luis Sanchez-Lopez, Javier Civera et al.

3D scene graphs hierarchically represent the environment appropriately organizing different environmental entities in various layers. Our previous work on situational graphs extends the concept of 3D scene graph to SLAM by tightly coupling the robot poses with the scene graph entities, achieving state-of-the-art results. Though, one of the limitations of S-Graphs is scalability in really large environments due to the increased graph size over time, increasing the computational complexity. To overcome this limitation in this work we present an initial research of an improved version of S-Graphs exploiting the hierarchy to reduce the graph size by marginalizing redundant robot poses and their connections to the observations of the same structural entities. Firstly, we propose the generation and optimization of room-local graphs encompassing all graph entities within a room-like structure. These room-local graphs are used to compress the S-Graphs marginalizing the redundant robot keyframes within the given room. We then perform windowed local optimization of the compressed graph at regular time-distance intervals. A global optimization of the compressed graph is performed every time a loop closure is detected. We show similar accuracy compared to the baseline while showing a 39.81% reduction in the computation time with respect to the baseline.

Zhenjun Zhao, Heng Yang, Bangyan Liao et al.

Global solvers have emerged as a powerful paradigm for 3D vision, offering certifiable solutions to nonconvex geometric optimization problems traditionally addressed by local or heuristic methods. This survey presents the first systematic review of global solvers in geometric vision, unifying the field through a comprehensive taxonomy of three core paradigms: Branch-and-Bound (BnB), Convex Relaxation (CR), and Graduated Non-Convexity (GNC). We present their theoretical foundations, algorithmic designs, and practical enhancements for robustness and scalability, examining how each addresses the fundamental nonconvexity of geometric estimation problems. Our analysis spans ten core vision tasks, from Wahba problem to bundle adjustment, revealing the optimality-robustness-scalability trade-offs that govern solver selection. We identify critical future directions: scaling algorithms while maintaining guarantees, integrating data-driven priors with certifiable optimization, establishing standardized benchmarks, and addressing societal implications for safety-critical deployment. By consolidating theoretical foundations, practical advances, and broader impacts, this survey provides a unified perspective and roadmap toward certifiable, trustworthy perception for real-world applications. A continuously-updated literature summary and companion code tutorials are available at https://github.com/ericzzj1989/Awesome-Global-Solvers-for-3D-Vision.

David Recasens, Robert Maier, Aljaz Bozic et al.

Gaussian Splatting (GS) has emerged as an efficient approach for high-quality novel view synthesis. While early GS variants struggled to accurately model the scene's geometry, recent advancements constraining the Gaussians' spread and shapes, such as 2D Gaussian Splatting, have significantly improved geometric fidelity. In this paper, we present Pixel-Aligned 1DoF Gaussian Splatting (PAGaS) that adapts the GS representation from novel view synthesis to the multi-view stereo depth task. Our key contribution is modeling a pixel's depth using one-degree-of-freedom (1DoF) Gaussians that remain tightly constrained during optimization. Unlike existing approaches, our Gaussians' positions and sizes are restricted by the back-projected pixel volumes, leaving depth as the sole degree of freedom to optimize. PAGaS produces highly detailed depths, as illustrated in Figure 1. We quantitatively validate these improvements on top of reference geometric and learning-based multi-view stereo baselines on challenging 3D reconstruction benchmarks. Code: davidrecasens.github.io/pagas

Nicolás Soncini, Javier Civera, Taihú Pire

While visual SLAM systems are well studied and achieve impressive results in indoor and urban settings, natural, outdoor and open-field environments are much less explored and still present relevant research challenges. Visual navigation and local mapping have shown a relatively good performance in open-field environments. However, globally consistent mapping and long-term localization still depend on the robustness of loop detection and closure, for which the literature is scarce. In this work we propose a novel method to pave the way towards robust loop detection in open fields, particularly in agricultural settings, based on local feature search and stereo geometric refinement, with a final stage of relative pose estimation. Our method consistently achieves good loop detections, with a median error of 15cm. We aim to characterize open fields as a novel environment for loop detection, understanding the limitations and problems that arise when dealing with them.

T. Berriel Martins, Javier Civera

3D Gaussian Splatting has emerged as a very promising scene representation, achieving state-of-the-art quality in novel view synthesis significantly faster than competing alternatives. However, its use of spherical harmonics to represent scene colors limits the expressivity of 3D Gaussians and, as a consequence, the capability of the representation to generalize as we move away from the training views. In this paper, we propose to encode the color information of 3D Gaussians into per-Gaussian feature vectors, which we denote as Feature Splatting (FeatSplat). To synthesize a novel view, Gaussians are first "splatted" into the image plane, then the corresponding feature vectors are alpha-blended, and finally the blended vector is decoded by a small MLP to render the RGB pixel values. To further inform the model, we concatenate a camera embedding to the blended feature vector, to condition the decoding also on the viewpoint information. Our experiments show that these novel model for encoding the radiance considerably improves novel view synthesis for low overlap views that are distant from the training views. Finally, we also show the capacity and convenience of our feature vector representation, demonstrating its capability not only to generate RGB values for novel views, but also their per-pixel semantic labels. Code available at https://github.com/tberriel/FeatSplat . Keywords: Gaussian Splatting, Novel View Synthesis, Feature Splatting

Alberto García-Hernández, Riccardo Giubilato, Klaus H. Strobl et al.

Perceptual aliasing and weak textures pose significant challenges to the task of place recognition, hindering the performance of Simultaneous Localization and Mapping (SLAM) systems. This paper presents a novel model, called UMF (standing for Unifying Local and Global Multimodal Features) that 1) leverages multi-modality by cross-attention blocks between vision and LiDAR features, and 2) includes a re-ranking stage that re-orders based on local feature matching the top-k candidates retrieved using a global representation. Our experiments, particularly on sequences captured on a planetary-analogous environment, show that UMF outperforms significantly previous baselines in those challenging aliased environments. Since our work aims to enhance the reliability of SLAM in all situations, we also explore its performance on the widely used RobotCar dataset, for broader applicability. Code and models are available at https://github.com/DLR-RM/UMF

Seong Hun Lee, Patrick Vandewalle, Javier Civera

We introduce NONSAC (Non-Minimal Sampling and Consensus), a general framework for robust and scalable model estimation from arbitrarily large datasets contaminated with noise and outliers. NONSAC repeatedly samples non-minimal subsets of data and generates model hypotheses using a robust estimator, producing multiple candidate models. The final model is selected based on a predefined scoring rule that evaluates hypothesis quality. Our framework is estimator-agnostic and can be integrated with existing geometric fitting algorithms such as RANSAC to improve both scalability and robustness to outliers. We propose and evaluate various scoring rules for NONSAC on relative camera pose estimation, Perspective-n-Point, and point cloud registration. Furthermore, we showcase the applicability of NONSAC to correspondence-free point cloud registration by hypothesizing all-to-all correspondences.

Seong Hun Lee, Javier Civera

We propose three novel metrics for evaluating the accuracy of a set of estimated camera poses given the ground truth: Translation Alignment Score (TAS), Rotation Alignment Score (RAS), and Pose Alignment Score (PAS). The TAS evaluates the translation accuracy independently of the rotations, and the RAS evaluates the rotation accuracy independently of the translations. The PAS is the average of the two scores, evaluating the combined accuracy of both translations and rotations. The TAS is computed in four steps: (1) Find the upper quartile of the closest-pair-distances, $d$. (2) Align the estimated trajectory to the ground truth using a robust registration method. (3) Collect all distance errors and obtain the cumulative frequencies for multiple thresholds ranging from $0.01d$ to $d$ with a resolution $0.01d$. (4) Add up these cumulative frequencies and normalize them such that the theoretical maximum is 1. The TAS has practical advantages over the existing metrics in that (1) it is robust to outliers and collinear motion, and (2) there is no need to adjust parameters on different datasets. The RAS is computed in a similar manner to the TAS and is also shown to be more robust against outliers than the existing rotation metrics. We verify our claims through extensive simulations and provide in-depth discussion of the strengths and weaknesses of the proposed metrics.

Samuel Cerezo, Seong Hun Lee, Javier Civera

In this letter, we present a closed-form initialization method that recovers the full visual-inertial state without nonlinear optimization. Unlike previous approaches that rely on iterative solvers, our formulation yields analytical, easy-to-implement, and numerically stable solutions for reliable start-up. Our method builds on small-rotation and constant-velocity approximations, which keep the formulation compact while preserving the essential coupling between motion and inertial measurements. We further propose an observability-driven, two-stage initialization scheme that balances accuracy with initialization latency. Extensive experiments on the EuRoC dataset validate our assumptions: our method achieves 10-20% lower initialization error than optimization-based approaches, while using 4x shorter initialization windows and reducing computational cost by 5x.

Tomas Berriel Martins, Martin R. Oswald, Javier Civera

Vision-language models have been key to the development of open-vocabulary 2D semantic segmentation. Lifting these models from 2D images to 3D scenes, however, remains a challenging problem. Existing approaches typically back-project and average 2D descriptors across views, or heuristically select a single representative one, often resulting in suboptimal 3D representations. In this work, we introduce a novel multiview transformer architecture that cross-attends across vision-language descriptors from multiple viewpoints and fuses them into a unified per-3D-instance embedding. As a second contribution, we leverage multiview consistency as a self-supervision signal for this fusion, which significantly improves performance when added to a standard supervised target-class loss. Our Cross-Attentive Multiview Fusion, which we denote with its acronym CAMFusion, not only consistently outperforms naive averaging or single-view descriptor selection, but also achieves state-of-the-art results on 3D semantic and instance classification benchmarks, including zero-shot evaluations on out-of-domain datasets.

Jiayao Mai, Bangyan Liao, Zhenjun Zhao et al.

The Homotopy paradigm, a general principle for solving challenging problems, appears across diverse domains such as robust optimization, global optimization, polynomial root-finding, and sampling. Practical solvers for these problems typically follow a predictor-corrector (PC) structure, but rely on hand-crafted heuristics for step sizes and iteration termination, which are often suboptimal and task-specific. To address this, we unify these problems under a single framework, which enables the design of a general neural solver. Building on this unified view, we propose Neural Predictor-Corrector (NPC), which replaces hand-crafted heuristics with automatically learned policies. NPC formulates policy selection as a sequential decision-making problem and leverages reinforcement learning to automatically discover efficient strategies. To further enhance generalization, we introduce an amortized training mechanism, enabling one-time offline training for a class of problems and efficient online inference on new instances. Experiments on four representative homotopy problems demonstrate that our method generalizes effectively to unseen instances. It consistently outperforms classical and specialized baselines in efficiency while demonstrating superior stability across tasks, highlighting the value of unifying homotopy methods into a single neural framework.

Zhengyi Xu, Yuhang Ming, Zhihao Zhan et al.

Multi-modal cross-view place recognition remains a fundamental challenge in computer vision and robotics due to the severe viewpoint, modality, and spatial-structure discrepancies between ground observations and aerial references. To address this challenge, we present MAG-VLAQ, a foundation-model-enhanced query aggregation framework for multi-modal aerial-ground cross-view place recognition. Specifically, our approach leverages pre-trained foundation models to extract dense visual tokens from both ground and aerial images, as well as expressive geometric tokens from ground LiDAR observations. These heterogeneous tokens are then projected into a shared embedding space for cross-modal alignment and fusion. As our main contribution, we propose ODE-conditioned VLAQ, which tightly couples neural ordinary differential equations (ODE)-based RGB-LiDAR fusion with vectors of locally aggregated queries (VLAQ). In this design, the VLAQ query centers are dynamically adapted according to the fused multi-modal state. This mechanism allows the final global descriptor to preserve globally learned retrieval prototypes while remaining responsive to scene-specific visual and geometric evidence, significantly improving aerial-ground matching. Extensive experiments on KITTI360-AG and nuScenes-AG validate the effectiveness of our proposed MAG-VLAQ. Notably, on KITTI360-AG, our MAG-VLAQ nearly doubles the state-of-the-art performance, achieving 61.1 Recall@1 in the satellite setting, compared with 34.5 from the closest competing approach.

Xiangqi Meng, Pengxu Hou, Zhenjun Zhao et al.

In addition to the core tasks of simultaneous localization and mapping (SLAM), active SLAM additionally in- volves generating robot actions that enable effective and efficient exploration of unknown environments. However, existing active SLAM pipelines are limited by three main factors. First, they inherit the restrictions of the underlying SLAM modules that they may be using. Second, their motion planning strategies are typically shortsighted and lack long-term vision. Third, most approaches struggle to handle dynamic scenes. To address these limitations, we propose a novel monocular active SLAM method, Dream-SLAM, which is based on dreaming cross-spatio-temporal images and semantically plausible structures of partially observed dynamic environments. The generated cross-spatio-temporal im- ages are fused with real observations to mitigate noise and data incompleteness, leading to more accurate camera pose estimation and a more coherent 3D scene representation. Furthermore, we integrate dreamed and observed scene structures to enable long- horizon planning, producing farsighted trajectories that promote efficient and thorough exploration. Extensive experiments on both public and self-collected datasets demonstrate that Dream-SLAM outperforms state-of-the-art methods in localization accuracy, mapping quality, and exploration efficiency. Source code will be publicly available upon paper acceptance.

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. This process typically involves two stages: 1) estimating the essential matrix between the views, and 2) disambiguating among the four candidate relative poses that satisfy the epipolar geometry. In this paper, we demonstrate a novel approach that, for the first time, bypasses the second stage. Specifically, we show that it is possible to directly estimate the correct relative camera pose from correspondences without needing a post-processing step to enforce the cheirality constraint on the correspondences. Building on recent advances in certifiable non-minimal optimization, we frame the relative pose estimation as a Quadratically Constrained Quadratic Program (QCQP). By applying the appropriate constraints, we ensure the estimation of a camera pose that corresponds to a valid 3D geometry and that is globally optimal when certified. We validate our method through exhaustive synthetic and real-world experiments, confirming the efficacy, efficiency and accuracy of the proposed approach. Code is available at https://github.com/javrtg/C2P.

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. In this work, we propose two post-hoc covariance estimates that can be plugged into any pretrained deep feature detector: a simple, isotropic covariance estimate that uses the predicted score at a given pixel location, and a full covariance estimate via the local structure tensor of the learned score maps. Both methods are easy to implement and can be applied to any deep feature detector. We show that these covariances are directly related to errors in feature matching, leading to improvements in downstream tasks, including solving the perspective-n-point problem and motion-only bundle adjustment. Code is available at https://github.com/javrtg/DAC

Manuel Bernal, Javier Civera

Developing real robotic systems requires a tight integration of mechanics, electronics and software. Most of the times, existing robotic platforms are either closed or expensive or both, and in-house solutions are costly to develop and maintain. Open-source and low-cost designs are essential to facilitate the access to real robotic platforms and enable further progress in the field. LoCoQuad is an arachnoid quadruped platform that we designed targeting research and education in robotics. To meet these two ends, our platform allows for a high degree of flexibility and configurability. Our legged design has the lowest hardware cost of the state of the art, in the range of 150-165USD. We validated the robot platform by running several experiments showing over all functionalities. All the mechanical and electronic designs and all the software have been made open source and can be found at: https://github.com/TomBlackroad/LoCoQuad

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. In this paper we propose a direct RGB-D SLAM algorithm with state-of-the-art accuracy and robustness at a los cost. Our experiments in the RGB-D TUM dataset [34] effectively show a better accuracy and robustness in CPU real time than direct RGB-D SLAM systems that make use of the GPU. The key ingredients of our approach are mainly two. Firstly, the combination of a semi-dense photometric and dense geometric error for the pose tracking (see Figure 1), which we demonstrate to be the most accurate alternative. And secondly, a model of the multi-view constraints and their errors in the mapping and tracking threads, which adds extra information over other approaches. We release the open-source implementation of our approach 1 . The reader is referred to a video with our results 2 for a more illustrative visualization of its performance.

Samuel Cerezo, Javier Civera

Deformable scenes violate the rigidity assumptions underpinning classical visual-inertial odometry (VIO), often leading to over-fitting to local non-rigid motion or severe drift when deformation dominates visual parallax. We introduce DefVINS, a visual-inertial odometry framework that explicitly separates a rigid, IMU-anchored state from a non--rigid warp represented by an embedded deformation graph. The system is initialized using a standard VIO procedure that fixes gravity, velocity, and IMU biases, after which non-rigid degrees of freedom are activated progressively as the estimation becomes well conditioned. An observability analysis is included to characterize how inertial measurements constrain the rigid motion and render otherwise unobservable modes identifiable in the presence of deformation. This analysis motivates the use of IMU anchoring and informs a conditioning-based activation strategy that prevents ill-posed updates under poor excitation. Ablation studies demonstrate the benefits of combining inertial constraints with observability-aware deformation activation, resulting in improved robustness under non-rigid environments.

Sergio Izquierdo, Mohamed Sayed, Michael Firman et al.

Computing accurate depth from multiple views is a fundamental and longstanding challenge in computer vision. However, most existing approaches do not generalize well across different domains and scene types (e.g. indoor vs. outdoor). Training a general-purpose multi-view stereo model is challenging and raises several questions, e.g. how to best make use of transformer-based architectures, how to incorporate additional metadata when there is a variable number of input views, and how to estimate the range of valid depths which can vary considerably across different scenes and is typically not known a priori? To address these issues, we introduce MVSA, a novel and versatile Multi-View Stereo architecture that aims to work Anywhere by generalizing across diverse domains and depth ranges. MVSA combines monocular and multi-view cues with an adaptive cost volume to deal with scale-related issues. We demonstrate state-of-the-art zero-shot depth estimation on the Robust Multi-View Depth Benchmark, surpassing existing multi-view stereo and monocular baselines.

Hriday Bavle, Jose Luis Sanchez-Lopez, Muhammad Shaheer et al.

The hierarchical structure of 3D scene graphs shows a high relevance for representations purposes, as it fits common patterns from man-made environments. But, additionally, the semantic and geometric information in such hierarchical representations could be leveraged to speed up the optimization and management of map elements and robot poses. In this direction, we present our work Situational Graphs 2.0 (S-Graphs 2.0), which leverages the hierarchical structure of indoor scenes for efficient data management and optimization. Our algorithm begins by constructing a situational graph that represents the environment into four layers: Keyframes, Walls, Rooms, and Floors. Our first novelty lies in the front-end, which includes a floor detection module capable of identifying stairways and assigning floor-level semantic relations to the underlying layers. Floor-level semantics allows us to propose a floor-based loop closure strategy, that effectively rejects false positive closures that typically appear due to aliasing between different floors of a building. Our second novelty lies in leveraging our representation hierarchy in the optimization. Our proposal consists of: (1) local optimization over a window of recent keyframes and their connected components across the four representation layers, (2) floor-level global optimization, which focuses only on keyframes and their connections within the current floor during loop closures, and (3) room-level local optimization, marginalizing redundant keyframes that share observations within the room, which reduces the computational footprint. We validate our algorithm extensively in different real multi-floor environments. Our approach shows state-of-art-art accuracy metrics in large-scale multi-floor environments, estimating hierarchical representations up to 10x faster, in average, than competing baselines

Tomas Berriel Martins, Martin R. Oswald, Javier Civera

This paper presents an Open-Vocabulary Online 3D semantic mapping pipeline, that we denote by its acronym OVO. Given a sequence of posed RGB-D frames, we detect and track 3D segments, which we describe using CLIP vectors. These are computed from the viewpoints where they are observed by a novel CLIP merging method. Notably, our OVO has a significantly lower computational and memory footprint than offline baselines, while also showing better segmentation metrics than offline and online ones. Along with superior segmentation performance, we also show experimental results of our mapping contributions integrated with two different full SLAM backbones (Gaussian-SLAM and ORB-SLAM2), being the first ones using a neural network to merge CLIP descriptors and demonstrating end-to-end open-vocabulary online 3D mapping with loop closure.

Alejandro Fontan, Tobias Fischer, Javier Civera et al.

Visual Simultaneous Localization and Mapping (VSLAM) research faces significant challenges due to fragmented toolchains, complex system configurations, and inconsistent evaluation methodologies. To address these issues, we present VSLAM-LAB, a unified framework designed to streamline the development, evaluation, and deployment of VSLAM systems. VSLAM-LAB simplifies the entire workflow by enabling seamless compilation and configuration of VSLAM algorithms, automated dataset downloading and preprocessing, and standardized experiment design, execution, and evaluation--all accessible through a single command-line interface. The framework supports a wide range of VSLAM systems and datasets, offering broad compatibility and extendability while promoting reproducibility through consistent evaluation metrics and analysis tools. By reducing implementation complexity and minimizing configuration overhead, VSLAM-LAB empowers researchers to focus on advancing VSLAM methodologies and accelerates progress toward scalable, real-world solutions. We demonstrate the ease with which user-relevant benchmarks can be created: here, we introduce difficulty-level-based categories, but one could envision environment-specific or condition-specific categories.

Alejandro Fontan, Javier Civera, Tobias Fischer et al.

Evaluation is critical to both developing and tuning Structure from Motion (SfM) and Visual SLAM (VSLAM) systems, but is universally reliant on high-quality geometric ground truth -- a resource that is not only costly and time-intensive but, in many cases, entirely unobtainable. This dependency on ground truth restricts SfM and SLAM applications across diverse environments and limits scalability to real-world scenarios. In this work, we propose a novel ground-truth-free (GTF) evaluation methodology that eliminates the need for geometric ground truth, instead using sensitivity estimation via sampling from both original and noisy versions of input images. Our approach shows strong correlation with traditional ground-truth-based benchmarks and supports GTF hyperparameter tuning. Removing the need for ground truth opens up new opportunities to leverage a much larger number of dataset sources, and for self-supervised and online tuning, with the potential for a data-driven breakthrough analogous to what has occurred in generative AI.

Hanyu Zhu, Zhihao Zhan, Yuhang Ming et al.

One of the central challenges in visual place recognition (VPR) is learning a robust global representation that remains discriminative under large viewpoint changes, illumination variations, and severe domain shifts. While visual foundation models (VFMs) provide strong local features, most existing methods rely on a single model, overlooking the complementary cues offered by different VFMs. However, exploiting such complementary information inevitably alters token distributions, which challenges the stability of existing query-based global aggregation schemes. To address these challenges, we propose DC-VLAQ, a representation-centric framework that integrates the fusion of complementary VFMs and robust global aggregation. Specifically, we first introduce a lightweight residual-guided complementary fusion that anchors representations in the DINOv2 feature space while injecting complementary semantics from CLIP through a learned residual correction. In addition, we propose the Vector of Local Aggregated Queries (VLAQ), a query--residual global aggregation scheme that encodes local tokens by their residual responses to learnable queries, resulting in improved stability and the preservation of fine-grained discriminative cues. Extensive experiments on standard VPR benchmarks, including Pitts30k, Tokyo24/7, MSLS, Nordland, SPED, and AmsterTime, demonstrate that DC-VLAQ consistently outperforms strong baselines and achieves state-of-the-art performance, particularly under challenging domain shifts and long-term appearance changes.

Seong Hun Lee, Patrick Vandewalle, Javier Civera

We revisit the classical Perspective-Three-Point (P3P) problem, which aims to recover the absolute pose of a calibrated camera from three 2D-3D correspondences. It has long been known that P3P can be reduced to a quartic polynomial with analytically simple and computationally efficient coefficients. However, this elegant formulation has been largely overlooked in modern literature. Building on the theoretical foundation that traces back to Grunert's work in 1841, we propose a compact algebraic solver that achieves accuracy and runtime comparable to state-of-the-art methods. Our results show that this classical formulation remains highly competitive when implemented with modern insights, offering an excellent balance between simplicity, efficiency, and accuracy.

Samuel Cerezo, Javier Civera

Initializing the state of a sensorized platform can be challenging, as a limited set of initial measurements often carry limited information, leading to poor initial estimates that may converge to local minima during non-linear optimization. This paper proposes a novel GNSS-inertial initialization strategy that delays the use of global GNSS measurements until sufficient information is available to accurately estimate the transformation between the GNSS and inertial frames. Instead, the method initially relies on GNSS relative distance residuals. To determine the optimal moment for switching to global measurements, we introduce a criterion based on the evolution of the Hessian matrix singular values. Experiments on the EuRoC and GVINS datasets show that our approach consistently outperforms the naive strategy of using global GNSS data from the start, yielding more accurate and robust initializations.

Samuel Cerezo, Gaetano Meli, Tomás Berriel Martins et al.

Models and methods originally developed for Novel View Synthesis and Scene Rendering, such as Neural Radiance Fields (NeRF) and Gaussian Splatting, are increasingly being adopted as representations in Simultaneous Localization and Mapping (SLAM). However, existing datasets fail to include the specific challenges of both fields, such as sequential operations and, in many settings, multi-modality in SLAM or generalization across viewpoints and illumination conditions in neural rendering. Additionally, the data are often collected using sensors which are handheld or mounted on drones or mobile robots, which complicates the accurate reproduction of sensor motions. To bridge these gaps, we introduce SLAM&Render, a novel dataset designed to benchmark methods in the intersection between SLAM, Novel View Rendering and Gaussian Splatting. Recorded with a robot manipulator, it uniquely includes 40 sequences with time-synchronized RGB-D images, IMU readings, robot kinematic data, and ground-truth pose streams. By releasing robot kinematic data, the dataset also enables the assessment of recent integrations of SLAM paradigms within robotic applications. The dataset features five setups with consumer and industrial objects under four controlled lighting conditions, each with separate training and test trajectories. All sequences are static with different levels of object rearrangements and occlusions. Our experimental results, obtained with several baselines from the literature, validate SLAM&Render as a relevant benchmark for this emerging research area.

Blanca Lasheras-Hernandez, Klaus H. Strobl, Sergio Izquierdo et al.

Metric depth estimation from visual sensors is crucial for robots to perceive, navigate, and interact with their environment. Traditional range imaging setups, such as stereo or structured light cameras, face hassles including calibration, occlusions, and hardware demands, with accuracy limited by the baseline between cameras. Single- and multi-view monocular depth offers a more compact alternative, but is constrained by the unobservability of the metric scale. Light field imaging provides a promising solution for estimating metric depth by using a unique lens configuration through a single device. However, its application to single-view dense metric depth is under-addressed mainly due to the technology's high cost, the lack of public benchmarks, and proprietary geometrical models and software. Our work explores the potential of focused plenoptic cameras for dense metric depth. We propose a novel pipeline that predicts metric depth from a single plenoptic camera shot by first generating a sparse metric point cloud using machine learning, which is then used to scale and align a dense relative depth map regressed by a foundation depth model, resulting in dense metric depth. To validate it, we curated the Light Field & Stereo Image Dataset (LFS) of real-world light field images with stereo depth labels, filling a current gap in existing resources. Experimental results show that our pipeline produces accurate metric depth predictions, laying a solid groundwork for future research in this field.

Samuel Cerezo, Javier Civera

In this paper, we introduce a novel formulation for camera motion estimation that integrates RGB-D images and inertial data through scene flow. Our goal is to accurately estimate the camera motion in a rigid 3D environment, along with the state of the inertial measurement unit (IMU). Our proposed method offers the flexibility to operate as a multi-frame optimization or to marginalize older data, thus effectively utilizing past measurements. To assess the performance of our method, we conducted evaluations using both synthetic data from the ICL-NUIM dataset and real data sequences from the OpenLORIS-Scene dataset. Our results show that the fusion of these two sensors enhances the accuracy of camera motion estimation when compared to using only visual data.

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. Our method, dubbed PCR-99, uses a deterministic 3-point sampling approach with two novel mechanisms that significantly boost the speed: (1) an improved ordering of the samples based on pairwise scale consistency, prioritizing the point correspondences that are more likely to be inliers, and (2) an efficient outlier rejection scheme based on triplet scale consistency, prescreening bad samples and reducing the number of hypotheses to be tested. Our evaluation shows that, up to 98% outlier ratio, the proposed method achieves comparable performance to the state of the art. At 99% outlier ratio, however, it outperforms the state of the art for both known-scale and unknown-scale problems. Especially for the latter, we observe a clear superiority in terms of robustness and speed.

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. Our Ray-Patch decoding reduces the computational footprint and increases inference speed up to one order of magnitude compared to previous models, without losing global attention, and hence maintaining specific task metrics. The key idea of our novel querying is to split the target image into a set of patches, then querying the transformer for each patch to extract a set of feature vectors, which are finally decoded into the target image using convolutional layers. Our experimental results, implementing Ray-Patch in 3 different architectures and evaluating it in 2 different tasks and datasets, demonstrate and quantify the effectiveness of our method, specifically a notable boost in rendering speed for the same task metrics.

Hriday Bavle, Jose Luis Sanchez-Lopez, Muhammad Shaheer et al.

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

Andrea Vallone, Frederik Warburg, Hans Hansen et al.

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

Alejandro Fontan, Laura Oliva, Javier Civera et al.

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.