Juan D. Tardós

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.

Víctor M. Batlle, José M. M. Montiel, Pascal Fua et al.

We propose a new approach to 3D reconstruction from sequences of images acquired by monocular endoscopes. It is based on two key insights. First, endoluminal cavities are watertight, a property naturally enforced by modeling them in terms of a signed distance function. Second, the scene illumination is variable. It comes from the endoscope's light sources and decays with the inverse of the squared distance to the surface. To exploit these insights, we build on NeuS, a neural implicit surface reconstruction technique with an outstanding capability to learn appearance and a SDF surface model from multiple views, but currently limited to scenes with static illumination. To remove this limitation and exploit the relation between pixel brightness and depth, we modify the NeuS architecture to explicitly account for it and introduce a calibrated photometric model of the endoscope's camera and light source. Our method is the first one to produce watertight reconstructions of whole colon sections. We demonstrate excellent accuracy on phantom imagery. Remarkably, the watertight prior combined with illumination decline, allows to complete the reconstruction of unseen portions of the surface with acceptable accuracy, paving the way to automatic quality assessment of cancer screening explorations, measuring the global percentage of observed mucosa.

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.

Javier Morlana, Juan D. Tardós, José M. M. Montiel

We introduce ColonSLAM, a system that combines classical multiple-map metric SLAM with deep features and topological priors to create topological maps of the whole colon. The SLAM pipeline by itself is able to create disconnected individual metric submaps representing locations from short video subsections of the colon, but is not able to merge covisible submaps due to deformations and the limited performance of the SIFT descriptor in the medical domain. ColonSLAM is guided by topological priors and combines a deep localization network trained to distinguish if two images come from the same place or not and the soft verification of a transformer-based matching network, being able to relate far-in-time submaps during an exploration, grouping them in nodes imaging the same colon place, building more complex maps than any other approach in the literature. We demonstrate our approach in the Endomapper dataset, showing its potential for producing maps of the whole colon in real human explorations. Code and models are available at: https://github.com/endomapper/ColonSLAM.

Javier Morlana, Juan D. Tardós, J. M. M. Montiel

We propose a topological mapping and localization system able to operate on real human colonoscopies, despite significant shape and illumination changes. The map is a graph where each node codes a colon location by a set of real images, while edges represent traversability between nodes. For close-in-time images, where scene changes are minor, place recognition can be successfully managed with the recent transformers-based local feature matching algorithms. However, under long-term changes -- such as different colonoscopies of the same patient -- feature-based matching fails. To address this, we train on real colonoscopies a deep global descriptor achieving high recall with significant changes in the scene. The addition of a Bayesian filter boosts the accuracy of long-term place recognition, enabling relocalization in a previously built map. Our experiments show that ColonMapper is able to autonomously build a map and localize against it in two important use cases: localization within the same colonoscopy or within different colonoscopies of the same patient. Code: https://github.com/jmorlana/ColonMapper.

Raúl Iranzo, Víctor M. Batlle, Juan D. Tardós et al.

Geometric reconstruction and SLAM with endoscopic images have advanced significantly in recent years. In most medical fields, monocular endoscopes are employed, and the algorithms used are typically adaptations of those designed for external environments, resulting in 3D reconstructions with an unknown scale factor. For the first time, we propose a method to estimate the real metric scale of a 3D reconstruction from standard monocular endoscopic images without relying on application-specific learned priors. Our fully model-based approach leverages the near-light sources embedded in endoscopes, positioned at a small but nonzero baseline from the camera, in combination with the inverse-square law of light attenuation, to accurately recover the metric scale from scratch. This enables the transformation of any endoscope into a metric device, which is crucial for applications such as measuring polyps, stenosis, or assessing the extent of diseased tissue.

Carlos Campos, Juan D. Tardós

We present a generic framework for scale-aware direct monocular odometry based on depth prediction from a deep neural network. In contrast with previous methods where depth information is only partially exploited, we formulate a novel depth prediction residual which allows us to incorporate multi-view depth information. In addition, we propose to use a truncated robust cost function which prevents considering inconsistent depth estimations. The photometric and depth-prediction measurements are integrated into a tightly-coupled optimization leading to a scale-aware monocular system which does not accumulate scale drift. Our proposal does not particularize for a concrete neural network, being able to work along with the vast majority of the existing depth prediction solutions. We demonstrate the validity and generality of our proposal evaluating it on the KITTI odometry dataset, using two publicly available neural networks and comparing it with similar approaches and the state-of-the-art for monocular and stereo SLAM. Experiments show that our proposal largely outperforms classic monocular SLAM, being 5 to 9 times more precise, beating similar approaches and having an accuracy which is closer to that of stereo systems.

Juan J. Gómez Rodríguez, José Lamarca, Javier Morlana et al.

Conventional SLAM techniques strongly rely on scene rigidity to solve data association, ignoring dynamic parts of the scene. In this work we present Semi-Direct DefSLAM (SD-DefSLAM), a novel monocular deformable SLAM method able to map highly deforming environments, built on top of DefSLAM. To robustly solve data association in challenging deforming scenes, SD-DefSLAM combines direct and indirect methods: an enhanced illumination-invariant Lucas-Kanade tracker for data association, geometric Bundle Adjustment for pose and deformable map estimation, and bag-of-words based on feature descriptors for camera relocation. Dynamic objects are detected and segmented-out using a CNN trained for the specific application domain. We thoroughly evaluate our system in two public datasets. The mandala dataset is a SLAM benchmark with increasingly aggressive deformations. The Hamlyn dataset contains intracorporeal sequences that pose serious real-life challenges beyond deformation like weak texture, specular reflections, surgical tools and occlusions. Our results show that SD-DefSLAM outperforms DefSLAM in point tracking, reconstruction accuracy and scale drift thanks to the improvement in all the data association steps, being the first system able to robustly perform SLAM inside the human body.

Berta Bescos, Carlos Campos, Juan D. Tardós et al.

The assumption of scene rigidity is common in visual SLAM algorithms. However, it limits their applicability in populated real-world environments. Furthermore, most scenarios including autonomous driving, multi-robot collaboration and augmented/virtual reality, require explicit motion information of the surroundings to help with decision making and scene understanding. We present in this paper DynaSLAM II, a visual SLAM system for stereo and RGB-D configurations that tightly integrates the multi-object tracking capability. DynaSLAM II makes use of instance semantic segmentation and of ORB features to track dynamic objects. The structure of the static scene and of the dynamic objects is optimized jointly with the trajectories of both the camera and the moving agents within a novel bundle adjustment proposal. The 3D bounding boxes of the objects are also estimated and loosely optimized within a fixed temporal window. We demonstrate that tracking dynamic objects does not only provide rich clues for scene understanding but is also beneficial for camera tracking. The project code will be released upon acceptance.

Carlos Campos, Richard Elvira, Juan J. Gómez Rodríguez et al.

This paper presents ORB-SLAM3, the first system able to perform visual, visual-inertial and multi-map SLAM with monocular, stereo and RGB-D cameras, using pin-hole and fisheye lens models. The first main novelty is a feature-based tightly-integrated visual-inertial SLAM system that fully relies on Maximum-a-Posteriori (MAP) estimation, even during the IMU initialization phase. The result is a system that operates robustly in real-time, in small and large, indoor and outdoor environments, and is 2 to 5 times more accurate than previous approaches. The second main novelty is a multiple map system that relies on a new place recognition method with improved recall. Thanks to it, ORB-SLAM3 is able to survive to long periods of poor visual information: when it gets lost, it starts a new map that will be seamlessly merged with previous maps when revisiting mapped areas. Compared with visual odometry systems that only use information from the last few seconds, ORB-SLAM3 is the first system able to reuse in all the algorithm stages all previous information. This allows to include in bundle adjustment co-visible keyframes, that provide high parallax observations boosting accuracy, even if they are widely separated in time or if they come from a previous mapping session. Our experiments show that, in all sensor configurations, ORB-SLAM3 is as robust as the best systems available in the literature, and significantly more accurate. Notably, our stereo-inertial SLAM achieves an average accuracy of 3.6 cm on the EuRoC drone and 9 mm under quick hand-held motions in the room of TUM-VI dataset, a setting representative of AR/VR scenarios. For the benefit of the community we make public the source code.

Carlos Campos, José M. M. Montiel, Juan D. Tardós

We formulate for the first time visual-inertial initialization as an optimal estimation problem, in the sense of maximum-a-posteriori (MAP) estimation. This allows us to properly take into account IMU measurement uncertainty, which was neglected in previous methods that either solved sets of algebraic equations, or minimized ad-hoc cost functions using least squares. Our exhaustive initialization tests on EuRoC dataset show that our proposal largely outperforms the best methods in the literature, being able to initialize in less than 4 seconds in almost any point of the trajectory, with a scale error of 5.3% on average. This initialization has been integrated into ORB-SLAM Visual-Inertial boosting its robustness and efficiency while maintaining its excellent accuracy.

Richard Elvira, Juan D. Tardós, J. M. M. Montiel

We propose ORBSLAM-Atlas, a system able to handle an unlimited number of disconnected sub-maps, that includes a robust map merging algorithm able to detect sub-maps with common regions and seamlessly fuse them. The outstanding robustness and accuracy of ORBSLAM are due to its ability to detect wide-baseline matches between keyframes, and to exploit them by means of non-linear optimization, however it only can handle a single map. ORBSLAM-Atlas brings the wide-baseline matching detection and exploitation to the multiple map arena. The result is a SLAM system significantly more general and robust, able to perform multi-session mapping. If tracking is lost during exploration, instead of freezing the map, a new sub-map is launched, and it can be fused with the previous map when common parts are visited. Our criteria to declare the camera lost contrast with previous approaches that simply count the number of tracked points, we propose to discard also inaccurately estimated camera poses due to bad geometrical conditioning. As a result, the map is split into more accurate sub-maps, that are eventually merged in a more accurate global map, thanks to the multi-mapping capabilities. We provide extensive experimental validation in the EuRoC datasets, where ORBSLAM-Atlas obtains accurate monocular and stereo results in the difficult sequences where ORBSLAM failed. We also build global maps after multiple sessions in the same room, obtaining the best results to date, between 2 and 3 times more accurate than competing multi-map approaches. We also show the robustness and capability of our system to deal with dynamic scenes, quantitatively in the EuRoC datasets and qualitatively in a densely populated corridor where camera occlusions and tracking losses are frequent.

Carlos Campos, J. M. M. Montiel, Juan D. Tardós

Visual-inertial SLAM (VI-SLAM) requires a good initial estimation of the initial velocity, orientation with respect to gravity and gyroscope and accelerometer biases. In this paper we build on the initialization method proposed by Martinelli and extended by Kaiser et al. , modifying it to be more general and efficient. We improve accuracy with several rounds of visual-inertial bundle adjustment, and robustify the method with novel observability and consensus tests, that discard erroneous solutions. Our results on the EuRoC dataset show that, while the original method produces scale errors up to 156%, our method is able to consistently initialize in less than two seconds with scale errors around 5%, which can be further reduced to less than 1% performing visual-inertial bundle adjustment after ten seconds.

Dorian Gálvez-López, Marta Salas, Juan D. Tardós et al.

We present a real-time object-based SLAM system that leverages the largest object database to date. Our approach comprises two main components: 1) a monocular SLAM algorithm that exploits object rigidity constraints to improve the map and find its real scale, and 2) a novel object recognition algorithm based on bags of binary words, which provides live detections with a database of 500 3D objects. The two components work together and benefit each other: the SLAM algorithm accumulates information from the observations of the objects, anchors object features to especial map landmarks and sets constrains on the optimization. At the same time, objects partially or fully located within the map are used as a prior to guide the recognition algorithm, achieving higher recall. We evaluate our proposal on five real environments showing improvements on the accuracy of the map and efficiency with respect to other state-of-the-art techniques.