Ana C. Murillo

Alberto Sabater, Luis Montesano, Ana C. Murillo

Event cameras are sensors of great interest for many applications that run in low-resource and challenging environments. They log sparse illumination changes with high temporal resolution and high dynamic range, while they present minimal power consumption. However, top-performing methods often ignore specific event-data properties, leading to the development of generic but computationally expensive algorithms. Efforts toward efficient solutions usually do not achieve top-accuracy results for complex tasks. This work proposes a novel framework, Event Transformer (EvT), that effectively takes advantage of event-data properties to be highly efficient and accurate. We introduce a new patch-based event representation and a compact transformer-like architecture to process it. EvT is evaluated on different event-based benchmarks for action and gesture recognition. Evaluation results show better or comparable accuracy to the state-of-the-art while requiring significantly less computation resources, which makes EvT able to work with minimal latency both on GPU and CPU.

Alberto Sabater, Luis Montesano, Ana C. Murillo

Event cameras record sparse illumination changes with high temporal resolution and high dynamic range. Thanks to their sparse recording and low consumption, they are increasingly used in applications such as AR/VR and autonomous driving. Current topperforming methods often ignore specific event-data properties, leading to the development of generic but computationally expensive algorithms, while event-aware methods do not perform as well. We propose Event Transformer+, that improves our seminal work EvT with a refined patch-based event representation and a more robust backbone to achieve more accurate results, while still benefiting from event-data sparsity to increase its efficiency. Additionally, we show how our system can work with different data modalities and propose specific output heads, for event-stream classification (i.e. action recognition) and per-pixel predictions (dense depth estimation). Evaluation results show better performance to the state-of-the-art while requiring minimal computation resources, both on GPU and CPU.

Carlos Plou, Pablo Pueyo, Ruben Martinez-Cantin et al.

Gen-Swarms is an innovative method that leverages and combines the capabilities of deep generative models with reactive navigation algorithms to automate the creation of drone shows. Advancements in deep generative models, particularly diffusion models, have demonstrated remarkable effectiveness in generating high-quality 2D images. Building on this success, various works have extended diffusion models to 3D point cloud generation. In contrast, alternative generative models such as flow matching have been proposed, offering a simple and intuitive transition from noise to meaningful outputs. However, the application of flow matching models to 3D point cloud generation remains largely unexplored. Gen-Swarms adapts these models to automatically generate drone shows. Existing 3D point cloud generative models create point trajectories which are impractical for drone swarms. In contrast, our method not only generates accurate 3D shapes but also guides the swarm motion, producing smooth trajectories and accounting for potential collisions through a reactive navigation algorithm incorporated into the sampling process. For example, when given a text category like Airplane, Gen-Swarms can rapidly and continuously generate numerous variations of 3D airplane shapes. Our experiments demonstrate that this approach is particularly well-suited for drone shows, providing feasible trajectories, creating representative final shapes, and significantly enhancing the overall performance of drone show generation.

Carlos Plou, Cesar Borja, Ruben Martinez-Cantin et al.

Finding information in hour-long videos is a challenging task even for top-performing Vision Language Models (VLMs), as encoding visual content quickly exceeds available context windows. To tackle this challenge, we present FALCONEye, a novel video agent based on a training-free, model-agnostic meta-architecture composed of a VLM and a Large Language Model (LLM). FALCONEye answers open-ended questions using an exploration-based search algorithm guided by calibrated confidence from the VLM's answers. We also introduce the FALCON-Bench benchmark, extending Question Answering problem to Video Answer Search-requiring models to return both the answer and its supporting temporal window for open-ended questions in hour-long videos. With just a 7B VLM and a lightweight LLM, FALCONEye outscores all open-source 7B VLMs and comparable agents in FALCON-Bench. It further demonstrates its generalization capability in MLVU benchmark with shorter videos and different tasks, surpassing GPT-4o on single-detail tasks while slashing inference cost by roughly an order of magnitude.

Inigo Alonso, Alberto Sabater, David Ferstl et al.

This work presents a novel approach for semi-supervised semantic segmentation. The key element of this approach is our contrastive learning module that enforces the segmentation network to yield similar pixel-level feature representations for same-class samples across the whole dataset. To achieve this, we maintain a memory bank continuously updated with relevant and high-quality feature vectors from labeled data. In an end-to-end training, the features from both labeled and unlabeled data are optimized to be similar to same-class samples from the memory bank. Our approach outperforms the current state-of-the-art for semi-supervised semantic segmentation and semi-supervised domain adaptation on well-known public benchmarks, with larger improvements on the most challenging scenarios, i.e., less available labeled data. https://github.com/Shathe/SemiSeg-Contrastive

O. Leon Barbed, José M. M. Montiel, Pascal Fua et al.

In this work, we focus on boosting the feature extraction to improve the performance of Structure-from-Motion (SfM) in endoscopy videos. We present SuperPoint-E, a new local feature extraction method that, using our proposed Tracking Adaptation supervision strategy, significantly improves the quality of feature detection and description in endoscopy. Extensive experimentation on real endoscopy recordings studies our approach's most suitable configuration and evaluates SuperPoint-E feature quality. The comparison with other baselines also shows that our 3D reconstructions are denser and cover more and longer video segments because our detector fires more densely and our features are more likely to survive (i.e. higher detection precision). In addition, our descriptor is more discriminative, making the guided matching step almost redundant. The presented approach brings significant improvements in the 3D reconstructions obtained, via SfM on endoscopy videos, compared to the original SuperPoint and the gold standard SfM COLMAP pipeline.

Sara Casao, Fernando Peña, Alberto Sabater et al.

The increase in non-biodegradable waste is a worldwide concern. Recycling facilities play a crucial role, but their automation is hindered by the complex characteristics of waste recycling lines like clutter or object deformation. In addition, the lack of publicly available labeled data for these environments makes developing robust perception systems challenging. Our work explores the benefits of multimodal perception for object segmentation in real waste management scenarios. First, we present SpectralWaste, the first dataset collected from an operational plastic waste sorting facility that provides synchronized hyperspectral and conventional RGB images. This dataset contains labels for several categories of objects that commonly appear in sorting plants and need to be detected and separated from the main trash flow for several reasons, such as security in the management line or reuse. Additionally, we propose a pipeline employing different object segmentation architectures and evaluate the alternatives on our dataset, conducting an extensive analysis for both multimodal and unimodal alternatives. Our evaluation pays special attention to efficiency and suitability for real-time processing and demonstrates how HSI can bring a boost to RGB-only perception in these realistic industrial settings without much computational overhead.

Pablo Pueyo, Eduardo Montijano, Ana C. Murillo et al.

This paper introduces CLIPSwarm, a new algorithm designed to automate the modeling of swarm drone formations based on natural language. The algorithm begins by enriching a provided word, to compose a text prompt that serves as input to an iterative approach to find the formation that best matches the provided word. The algorithm iteratively refines formations of robots to align with the textual description, employing different steps for "exploration" and "exploitation". Our framework is currently evaluated on simple formation targets, limited to contour shapes. A formation is visually represented through alpha-shape contours and the most representative color is automatically found for the input word. To measure the similarity between the description and the visual representation of the formation, we use CLIP [1], encoding text and images into vectors and assessing their similarity. Subsequently, the algorithm rearranges the formation to visually represent the word more effectively, within the given constraints of available drones. Control actions are then assigned to the drones, ensuring robotic behavior and collision-free movement. Experimental results demonstrate the system's efficacy in accurately modeling robot formations from natural language descriptions. The algorithm's versatility is showcased through the execution of drone shows in photorealistic simulation with varying shapes. We refer the reader to the supplementary video for a visual reference of the results.

Carlos Plou, Nerea Gallego, Alberto Sabater et al.

Event cameras are a promising technology for activity recognition in dark environments due to their unique properties. However, real event camera datasets under low-lighting conditions are still scarce, which also limits the number of approaches to solve these kind of problems, hindering the potential of this technology in many applications. We present EventSleep, a new dataset and methodology to address this gap and study the suitability of event cameras for a very relevant medical application: sleep monitoring for sleep disorders analysis. The dataset contains synchronized event and infrared recordings emulating common movements that happen during the sleep, resulting in a new challenging and unique dataset for activity recognition in dark environments. Our novel pipeline is able to achieve high accuracy under these challenging conditions and incorporates a Bayesian approach (Laplace ensembles) to increase the robustness in the predictions, which is fundamental for medical applications. Our work is the first application of Bayesian neural networks for event cameras, the first use of Laplace ensembles in a realistic problem, and also demonstrates for the first time the potential of event cameras in a new application domain: to enhance current sleep evaluation procedures. Our activity recognition results highlight the potential of event cameras under dark conditions, and its capacity and robustness for sleep activity recognition, and open problems as the adaptation of event data pre-processing techniques to dark environments.

César Borja, Carlos Plou, Rubén Martinez-Cantín et al.

Semantic segmentation is essential to automate underwater imagery analysis with ecology monitoring purposes. Unfortunately, fine grained underwater scene analysis is still an open problem even for top performing segmentation models. The high cost of obtaining dense, expert-annotated, segmentation labels hinders the supervision of models in this domain. While sparse point-labels are easier to obtain, they introduce challenges regarding which points to annotate and how to propagate the sparse information. We present SparseUWSeg, a novel framework that addresses both issues. SparseUWSeg employs an active sampling strategy to guide annotators, maximizing the value of their point labels. Then, it propagates these sparse labels with a hybrid approach leverages both the best of SAM2 and superpixel-based methods. Experiments on two diverse underwater datasets demonstrate the benefits of SparseUWSeg over state-of-the-art approaches, achieving up to +5\% mIoU over D+NN. Our main contribution is the design and release of a simple but effective interactive annotation tool, integrating our algorithms. It enables ecology researchers to leverage foundation models and computer vision to efficiently generate high-quality segmentation masks to process their data.

Clara Tomasini, Luis Riazuelo, Ana C. Murillo

Video bronchoscopy is a fundamental procedure in respiratory medicine, where medical experts navigate through the bronchial tree of a patient to diagnose or operate the patient. Surgeons need to determine the position of the scope as they go through the airway until they reach the area of interest. This task is very challenging for practitioners due to the complex bronchial tree structure and varying doctor experience and training. Navigation assistance to locate the bronchoscope during the procedure can improve its outcome. Currently used techniques for navigational guidance commonly rely on previous CT scans of the patient to obtain a 3D model of the airway, followed by tracking of the scope with additional sensors or image registration. These methods obtain accurate locations but imply additional setup, scans and training. Accurate metric localization is not always required, and a topological localization with regard to a generic airway model can often suffice to assist the surgeon with navigation. We present an image-based bronchoscopy topological localization pipeline to provide navigation assistance during the procedure, with no need of patient CT scan. Our approach is trained only on phantom data, eliminating the high cost of real data labeling, and presents good generalization capabilities. The results obtained surpass existing methods, particularly on real data test sequences.

Clara Tomasini, Luis Riazuelo, Ana C. Murillo

Automatic segmentation of anatomical landmarks in endoscopic images can provide assistance to doctors and surgeons for diagnosis, treatments or medical training. However, obtaining the annotations required to train commonly used supervised learning methods is a tedious and difficult task, in particular for real images. While ground truth annotations are easier to obtain for synthetic data, models trained on such data often do not generalize well to real data. Generative approaches can add realistic texture to it, but face difficulties to maintain the structure of the original scene. The main contribution in this work is a novel image translation model that adds realistic texture to simulated endoscopic images while keeping the key scene layout information. Our approach produces realistic images in different endoscopy scenarios. We demonstrate these images can effectively be used to successfully train a model for a challenging end task without any real labeled data. In particular, we demonstrate our approach for the task of fold segmentation in colonoscopy images. Folds are key anatomical landmarks that can occlude parts of the colon mucosa and possible polyps. Our approach generates realistic images maintaining the shape and location of the original folds, after the image-style-translation, better than existing methods. We run experiments both on a novel simulated dataset for fold segmentation, and real data from the EndoMapper (EM) dataset. All our new generated data and new EM metadata is being released to facilitate further research, as no public benchmark is currently available for the task of fold segmentation.

Carlos Plou, Lorenzo Mur-Labadia, Ruben Martinez-Cantin et al.

The goal of the Step Grounding task is to locate temporal boundaries of activities based on natural language descriptions. This technical report introduces a Bayesian-VSLNet to address the challenge of identifying such temporal segments in lengthy, untrimmed egocentric videos. Our model significantly improves upon traditional models by incorporating a novel Bayesian temporal-order prior during inference, enhancing the accuracy of moment predictions. This prior adjusts for cyclic and repetitive actions within videos. Our evaluations demonstrate superior performance over existing methods, achieving state-of-the-art results on the Ego4D Goal-Step dataset with a 35.18 Recall Top-1 at 0.3 IoU and 20.48 Recall Top-1 at 0.5 IoU on the test set.

Carlos Plou, Ana C. Murillo, Ruben Martinez-Cantin

Efficiently tackling multiple tasks within complex environment, such as those found in robot manipulation, remains an ongoing challenge in robotics and an opportunity for data-driven solutions, such as reinforcement learning (RL). Model-based RL, by building a dynamic model of the robot, enables data reuse and transfer learning between tasks with the same robot and similar environment. Furthermore, data gathering in robotics is expensive and we must rely on data efficient approaches such as model-based RL, where policy learning is mostly conducted on cheaper simulations based on the learned model. Therefore, the quality of the model is fundamental for the performance of the posterior tasks. In this work, we focus on improving the quality of the model and maintaining the data efficiency by performing active learning of the dynamic model during a preliminary exploration phase based on maximize information gathering. We employ Bayesian neural network models to represent, in a probabilistic way, both the belief and information encoded in the dynamic model during exploration. With our presented strategies we manage to actively estimate the novelty of each transition, using this as the exploration reward. In this work, we compare several Bayesian inference methods for neural networks, some of which have never been used in a robotics context, and evaluate them in a realistic robot manipulation setup. Our experiments show the advantages of our Bayesian model-based RL approach, with similar quality in the results than relevant alternatives with much lower requirements regarding robot execution steps. Unlike related previous studies that focused the validation solely on toy problems, our research takes a step towards more realistic setups, tackling robotic arm end-tasks.

Pablo Pueyo, Eduardo Montijano, Ana C. Murillo et al.

We present CineMPC, an algorithm to autonomously control a UAV-borne video camera in a nonlinear Model Predicted Control (MPC) loop. CineMPC controls both the position and orientation of the camera -- the camera extrinsics -- as well as the lens focal length, focal distance, and aperture -- the camera intrinsics. While some existing solutions autonomously control the position and orientation of the camera, no existing solutions also control the intrinsic parameters, which are essential tools for rich cinematographic expression. The intrinsic parameters control the parts of the scene that are focused or blurred, the viewers' perception of depth in the scene and the position of the targets in the image. CineMPC closes the loop from camera images to UAV trajectory and lens parameters in order to follow the desired relative trajectory and image composition as the targets move through the scene. Experiments using a photo-realistic environment demonstrate the capabilities of the proposed control framework to successfully achieve a full array of cinematographic effects not possible without full camera control.

Alberto Sabater, Iñigo Alonso, Luis Montesano et al.

Hand action recognition is a special case of action recognition with applications in human-robot interaction, virtual reality or life-logging systems. Building action classifiers able to work for such heterogeneous action domains is very challenging. There are very subtle changes across different actions from a given application but also large variations across domains (e.g. virtual reality vs life-logging). This work introduces a novel skeleton-based hand motion representation model that tackles this problem. The framework we propose is agnostic to the application domain or camera recording view-point. When working on a single domain (intra-domain action classification) our approach performs better or similar to current state-of-the-art methods on well-known hand action recognition benchmarks. And, more importantly, when performing hand action recognition for action domains and camera perspectives which our approach has not been trained for (cross-domain action classification), our proposed framework achieves comparable performance to intra-domain state-of-the-art methods. These experiments show the robustness and generalization capabilities of our framework.

Alberto Sabater, Laura Santos, Jose Santos-Victor et al.

One-shot action recognition aims to recognize new action categories from a single reference example, typically referred to as the anchor example. This work presents a novel approach for one-shot action recognition in the wild that computes motion representations robust to variable kinematic conditions. One-shot action recognition is then performed by evaluating anchor and target motion representations. We also develop a set of complementary steps that boost the action recognition performance in the most challenging scenarios. Our approach is evaluated on the public NTU-120 one-shot action recognition benchmark, outperforming previous action recognition models. Besides, we evaluate our framework on a real use-case of therapy with autistic people. These recordings are particularly challenging due to high-level artifacts from the patient motion. Our results provide not only quantitative but also online qualitative measures, essential for the patient evaluation and monitoring during the actual therapy.

Sara Casao, Abel Naya, Ana C. Murillo et al.

Most recent works on multi-target tracking with multiple cameras focus on centralized systems. In contrast, this paper presents a multi-target tracking approach implemented in a distributed camera network. The advantages of distributed systems lie in lighter communication management, greater robustness to failures and local decision making. On the other hand, data association and information fusion are more challenging than in a centralized setup, mostly due to the lack of global and complete information. The proposed algorithm boosts the benefits of the Distributed-Consensus Kalman Filter with the support of a re-identification network and a distributed tracker manager module to facilitate consistent information. These techniques complement each other and facilitate the cross-camera data association in a simple and effective manner. We evaluate the whole system with known public data sets under different conditions demonstrating the advantages of combining all the modules. In addition, we compare our algorithm to some existing centralized tracking methods, outperforming their behavior in terms of accuracy and bandwidth usage.

Inigo Alonso, Luis Riazuelo, Luis Montesano et al.

LiDAR semantic segmentation provides 3D semantic information about the environment, an essential cue for intelligent systems during their decision making processes. Deep neural networks are achieving state-of-the-art results on large public benchmarks on this task. Unfortunately, finding models that generalize well or adapt to additional domains, where data distribution is different, remains a major challenge. This work addresses the problem of unsupervised domain adaptation for LiDAR semantic segmentation models. Our approach combines novel ideas on top of the current state-of-the-art approaches and yields new state-of-the-art results. We propose simple but effective strategies to reduce the domain shift by aligning the data distribution on the input space. Besides, we propose a learning-based approach that aligns the distribution of the semantic classes of the target domain to the source domain. The presented ablation study shows how each part contributes to the final performance. Our strategy is shown to outperform previous approaches for domain adaptation with comparisons run on three different domains.

Alberto Sabater, Luis Montesano, Ana C. Murillo

Object recognition in video is an important task for plenty of applications, including autonomous driving perception, surveillance tasks, wearable devices or IoT networks. Object recognition using video data is more challenging than using still images due to blur, occlusions or rare object poses. Specific video detectors with high computational cost or standard image detectors together with a fast post-processing algorithm achieve the current state-of-the-art. This work introduces a novel post-processing pipeline that overcomes some of the limitations of previous post-processing methods by introducing a learning-based similarity evaluation between detections across frames. Our method improves the results of state-of-the-art specific video detectors, specially regarding fast moving objects, and presents low resource requirements. And applied to efficient still image detectors, such as YOLO, provides comparable results to much more computationally intensive detectors.

Alberto Sabater, Luis Montesano, Ana C. Murillo

Wearable technologies are enabling plenty of new applications of computer vision, from life logging to health assistance. Many of them are required to recognize the elements of interest in the scene captured by the camera. This work studies the problem of object detection and localization on videos captured by this type of camera. Wearable videos are a much more challenging scenario for object detection than standard images or even another type of videos, due to lower quality images (e.g. poor focus) or high clutter and occlusion common in wearable recordings. Existing work typically focuses on detecting the objects of focus or those being manipulated by the user wearing the camera. We perform a more general evaluation of the task of object detection in this type of video, because numerous applications, such as marketing studies, also need detecting objects which are not in focus by the user. This work presents a thorough study of the well known YOLO architecture, that offers an excellent trade-off between accuracy and speed, for the particular case of object detection in wearable video. We focus our study on the public ADL Dataset, but we also use additional public data for complementary evaluations. We run an exhaustive set of experiments with different variations of the original architecture and its training strategy. Our experiments drive to several conclusions about the most promising directions for our goal and point us to further research steps to improve detection in wearable videos.

Iñigo Alonso, Luis Riazuelo, Luis Montesano et al.

LIDAR semantic segmentation, which assigns a semantic label to each 3D point measured by the LIDAR, is becoming an essential task for many robotic applications such as autonomous driving. Fast and efficient semantic segmentation methods are needed to match the strong computational and temporal restrictions of many of these real-world applications. This work presents 3D-MiniNet, a novel approach for LIDAR semantic segmentation that combines 3D and 2D learning layers. It first learns a 2D representation from the raw points through a novel projection which extracts local and global information from the 3D data. This representation is fed to an efficient 2D Fully Convolutional Neural Network (FCNN) that produces a 2D semantic segmentation. These 2D semantic labels are re-projected back to the 3D space and enhanced through a post-processing module. The main novelty in our strategy relies on the projection learning module. Our detailed ablation study shows how each component contributes to the final performance of 3D-MiniNet. We validate our approach on well known public benchmarks (SemanticKITTI and KITTI), where 3D-MiniNet gets state-of-the-art results while being faster and more parameter-efficient than previous methods.

Iñigo Alonso, Ana C. Murillo

Event cameras, or Dynamic Vision Sensor (DVS), are very promising sensors which have shown several advantages over frame based cameras. However, most recent work on real applications of these cameras is focused on 3D reconstruction and 6-DOF camera tracking. Deep learning based approaches, which are leading the state-of-the-art in visual recognition tasks, could potentially take advantage of the benefits of DVS, but some adaptations are needed still needed in order to effectively work on these cameras. This work introduces a first baseline for semantic segmentation with this kind of data. We build a semantic segmentation CNN based on state-of-the-art techniques which takes event information as the only input. Besides, we propose a novel representation for DVS data that outperforms previously used event representations for related tasks. Since there is no existing labeled dataset for this task, we propose how to automatically generate approximated semantic segmentation labels for some sequences of the DDD17 dataset, which we publish together with the model, and demonstrate they are valid to train a model for DVS data only. We compare our results on semantic segmentation from DVS data with results using corresponding grayscale images, demonstrating how they are complementary and worth combining.