Daniele Cattaneo

Maximilian Luz, Rohit Mohan, Thomas Nürnberg et al.

Capturing 4D spatiotemporal surroundings is crucial for the safe and reliable operation of robots in dynamic environments. However, most existing methods address only one side of the problem: they either provide coarse geometric tracking via bounding boxes, or detailed 3D structures like voxel-based occupancy that lack explicit temporal association. In this work, we present Latent Gaussian Splatting for 4D Panoptic Occupancy Tracking (LaGS) that advances spatiotemporal scene understanding in a holistic direction. Our approach incorporates camera-based end-to-end tracking with mask-based multi-view panoptic occupancy prediction, and addresses the key challenge of efficiently aggregating multi-view information into 3D voxel grids via a novel latent Gaussian splatting approach. Specifically, we first fuse observations into 3D Gaussians that serve as a sparse point-centric latent representation of the 3D scene, and then splat the aggregated features onto a 3D voxel grid that is decoded by a mask-based segmentation head. We evaluate LaGS on the Occ3D nuScenes and Waymo datasets, achieving state-of-the-art performance for 4D panoptic occupancy tracking. We make our code available at https://lags.cs.uni-freiburg.de/.

Rohit Mohan, José Arce, Sassan Mokhtar et al.

Safety and efficiency are paramount in healthcare facilities where the lives of patients are at stake. Despite the adoption of robots to assist medical staff in challenging tasks such as complex surgeries, human expertise is still indispensable. The next generation of autonomous healthcare robots hinges on their capacity to perceive and understand their complex and frenetic environments. While deep learning models are increasingly used for this purpose, they require extensive annotated training data which is impractical to obtain in real-world healthcare settings. To bridge this gap, we present Syn-Mediverse, the first hyper-realistic multimodal synthetic dataset of diverse healthcare facilities. Syn-Mediverse contains over \num{48000} images from a simulated industry-standard optical tracking camera and provides more than 1.5M annotations spanning five different scene understanding tasks including depth estimation, object detection, semantic segmentation, instance segmentation, and panoptic segmentation. We demonstrate the complexity of our dataset by evaluating the performance on a broad range of state-of-the-art baselines for each task. To further advance research on scene understanding of healthcare facilities, along with the public dataset we provide an online evaluation benchmark available at \url{http://syn-mediverse.cs.uni-freiburg.de}

Abhijeet Nayak, Daniele Cattaneo, Abhinav Valada

Localization is paramount for autonomous robots. While camera and LiDAR-based approaches have been extensively investigated, they are affected by adverse illumination and weather conditions. Therefore, radar sensors have recently gained attention due to their intrinsic robustness to such conditions. In this paper, we propose RaLF, a novel deep neural network-based approach for localizing radar scans in a LiDAR map of the environment, by jointly learning to address both place recognition and metric localization. RaLF is composed of radar and LiDAR feature encoders, a place recognition head that generates global descriptors, and a metric localization head that predicts the 3-DoF transformation between the radar scan and the map. We tackle the place recognition task by learning a shared embedding space between the two modalities via cross-modal metric learning. Additionally, we perform metric localization by predicting pixel-level flow vectors that align the query radar scan with the LiDAR map. We extensively evaluate our approach on multiple real-world driving datasets and show that RaLF achieves state-of-the-art performance for both place recognition and metric localization. Moreover, we demonstrate that our approach can effectively generalize to different cities and sensor setups than the ones used during training. We make the code and trained models publicly available at http://ralf.cs.uni-freiburg.de.

Julia Hindel, Simon Bultmann, Houman Masnavi et al.

Self-supervised online traversability estimation enables robots to continuously learn from unlabeled open-world experiences and adapt their navigation behavior toward safe and efficient trajectories. Existing approaches either rely on handcrafted proprioceptive traversability scores, limiting robot-agnosticism, or cluster prior data, preventing online learning. Moreover, many continual learning methods incur substantial memory and computational costs, hindering onboard deployment. We introduce COTRATE, an online learning framework for continuous traversability estimation from multimodal, unlabeled robot experience. Our method first infers robust traversability scores using a robot-agnostic, learning-based online terrain assessment module operating on proprioceptiveand inertial signals. These scores then supervise a visual traversability network through a novel alignment loss that associates visual embeddings with online terrain assessments.To mitigate forgetting during continual learning with minimal overhead, we propose a diversity-aware feature selection strategythat preserves performance using a compact replay memory. We further show that the learned traversability representation supports knowledge transfer across different robot platforms with different locomotion kinematics. We evaluate COTRATE on a dataset of \approx 50,000 images collected with two robotic platforms across 11 outdoor terrains, and benchmark it on navigation tasks in three representative outdoor environments. We make the dataset, code, and trained models publicly available.

Julia Hindel, Daniele Cattaneo, Abhinav Valada

Semantic segmentation models are typically trained on a fixed set of classes, limiting their applicability in open-world scenarios. Class-incremental semantic segmentation aims to update models with emerging new classes while preventing catastrophic forgetting of previously learned ones. However, existing methods impose strict rigidity on old classes, reducing their effectiveness in learning new incremental classes. In this work, we propose Taxonomy-Oriented Poincaré-regularized Incremental-Class Segmentation (TOPICS) that learns feature embeddings in hyperbolic space following explicit taxonomy-tree structures. This supervision provides plasticity for old classes, updating ancestors based on new classes while integrating new classes at fitting positions. Additionally, we maintain implicit class relational constraints on the geometric basis of the Poincaré ball. This ensures that the latent space can continuously adapt to new constraints while maintaining a robust structure to combat catastrophic forgetting. We also establish eight realistic incremental learning protocols for autonomous driving scenarios, where novel classes can originate from known classes or the background. Extensive evaluations of TOPICS on the Cityscapes and Mapillary Vistas 2.0 benchmarks demonstrate that it achieves state-of-the-art performance. We make the code and trained models publicly available at http://topics.cs.uni-freiburg.de.

Simon Bultmann, Daniele Cattaneo, Abhinav Valada

Accurate camera-LiDAR calibration is a prerequisite for robust multi-modal perception in robotics. Recent target-less approaches based on deep point correspondences achieve remarkable performance for extrinsic calibration but assume rectified images with known intrinsics. In this work, we overcome this limitation and present the first fully target-less pipeline that jointly estimates camera intrinsics (pinhole model with radial-tangential distortion) and camera-LiDAR extrinsics with deep pixel-point correspondences. Our approach extends deep correspondence-based calibration by (i) automatic intrinsic initialization via structure-from-motion, (ii) generalizing camera-LiDAR matching to raw images with unknown intrinsics including distortion, and (iii) tightly coupling correspondence estimation with joint nonlinear optimization over both intrinsics and extrinsics. We evaluate our method on the KITTI dataset with unseen camera-LiDAR pairs and demonstrate that joint calibration achieves improved extrinsic accuracy while additionally recovering accurate intrinsics.

Rohit Mohan, Florian Drews, Yakov Miron et al.

LiDAR-camera fusion enhances 3D panoptic segmentation by leveraging camera images to complement sparse LiDAR scans, but it also introduces a critical failure mode. Under adverse conditions, degradation or failure of the camera sensor can significantly compromise the reliability of the perception system. To address this problem, we introduce UP-Fuse, a novel uncertainty-aware fusion framework in the 2D range-view that remains robust under camera sensor degradation, calibration drift, and sensor failure. Raw LiDAR data is first projected into the range-view and encoded by a LiDAR encoder, while camera features are simultaneously extracted and projected into the same shared space. At its core, UP-Fuse employs an uncertainty-guided fusion module that dynamically modulates cross-modal interaction using predicted uncertainty maps. These maps are learned by quantifying representational divergence under diverse visual degradations, ensuring that only reliable visual cues influence the fused representation. The fused range-view features are decoded by a novel hybrid 2D-3D transformer that mitigates spatial ambiguities inherent to the 2D projection and directly predicts 3D panoptic segmentation masks. Extensive experiments on Panoptic nuScenes, SemanticKITTI, and our introduced Panoptic Waymo benchmark demonstrate the efficacy and robustness of UP-Fuse, which maintains strong performance even under severe visual corruption or misalignment, making it well suited for robotic perception in safety-critical settings.

Martin Büchner, Liza Dahiya, Simon Dorer et al.

Visual loop closure detection traditionally relies on place recognition methods to retrieve candidate loops that are validated using computationally expensive RANSAC-based geometric verification. As false positive loop closures significantly degrade downstream pose graph estimates, verifying a large number of candidates in online simultaneous localization and mapping scenarios is constrained by limited time and compute resources. While most deep loop closure detection approaches only operate on pairs of keyframes, we relax this constraint by considering neighborhoods of multiple keyframes when detecting loops. In this work, we introduce LoopGNN, a graph neural network architecture that estimates loop closure consensus by leveraging cliques of visually similar keyframes retrieved through place recognition. By propagating deep feature encodings among nodes of the clique, our method yields high-precision estimates while maintaining high recall. Extensive experimental evaluations on the TartanDrive 2.0 and NCLT datasets demonstrate that LoopGNN outperforms traditional baselines. Additionally, an ablation study across various keypoint extractors demonstrates that our method is robust, regardless of the type of deep feature encodings used, and exhibits higher computational efficiency compared to classical geometric verification baselines. We release our code, supplementary material, and keyframe data at https://loopgnn.cs.uni-freiburg.de.

Daniele Cattaneo, Abhinav Valada

LiDARs are widely used for mapping and localization in dynamic environments. However, their high cost limits their widespread adoption. On the other hand, monocular localization in LiDAR maps using inexpensive cameras is a cost-effective alternative for large-scale deployment. Nevertheless, most existing approaches struggle to generalize to new sensor setups and environments, requiring retraining or fine-tuning. In this paper, we present CMRNext, a novel approach for camera-LIDAR matching that is independent of sensor-specific parameters, generalizable, and can be used in the wild for monocular localization in LiDAR maps and camera-LiDAR extrinsic calibration. CMRNext exploits recent advances in deep neural networks for matching cross-modal data and standard geometric techniques for robust pose estimation. We reformulate the point-pixel matching problem as an optical flow estimation problem and solve the Perspective-n-Point problem based on the resulting correspondences to find the relative pose between the camera and the LiDAR point cloud. We extensively evaluate CMRNext on six different robotic platforms, including three publicly available datasets and three in-house robots. Our experimental evaluations demonstrate that CMRNext outperforms existing approaches on both tasks and effectively generalizes to previously unseen environments and sensor setups in a zero-shot manner. We make the code and pre-trained models publicly available at http://cmrnext.cs.uni-freiburg.de .

Julia Hindel, Rohit Mohan, Jelena Bratulic et al.

LiDAR semantic segmentation models are typically trained from random initialization as universal pre-training is hindered by the lack of large, diverse datasets. Moreover, most point cloud segmentation architectures incorporate custom network layers, limiting the transferability of advances from vision-based architectures. Inspired by recent advances in universal foundation models, we propose BALViT, a novel approach that leverages frozen vision models as amodal feature encoders for learning strong LiDAR encoders. Specifically, BALViT incorporates both range-view and bird's-eye-view LiDAR encoding mechanisms, which we combine through a novel 2D-3D adapter. While the range-view features are processed through a frozen image backbone, our bird's-eye-view branch enhances them through multiple cross-attention interactions. Thereby, we continuously improve the vision network with domain-dependent knowledge, resulting in a strong label-efficient LiDAR encoding mechanism. Extensive evaluations of BALViT on the SemanticKITTI and nuScenes benchmarks demonstrate that it outperforms state-of-the-art methods on small data regimes. We make the code and models publicly available at: http://balvit.cs.uni-freiburg.de.

Markus Käppeler, Özgün Çiçek, Daniele Cattaneo et al.

Camera-based 3D object detection and tracking are essential for perception in autonomous driving. Current state-of-the-art approaches often rely exclusively on either perspective-view (PV) or bird's-eye-view (BEV) features, limiting their ability to leverage both fine-grained object details and spatially structured scene representations. In this work, we propose DualViewDistill, a hybrid detection and tracking framework that incorporates both PV and BEV camera image features to leverage their complementary strengths. Our approach introduces BEV maps guided by foundation models, leveraging descriptive DINOv2 features that are distilled into BEV representations through a novel distillation process. By integrating PV features with BEV maps enriched with semantic and geometric features from DINOv2, our model leverages this hybrid representation via deformable aggregation to enhance 3D object detection and tracking. Extensive experiments on the nuScenes and Argoverse 2 benchmarks demonstrate that DualViewDistill achieves state-of-the-art performance. The results showcase the potential of foundation model BEV maps to enable more reliable perception for autonomous driving. We make the code and pre-trained models available at https://dualviewdistill.cs.uni-freiburg.de .

Julia Hindel, Ema Mekic, Enamundram Naga Karthik et al.

Robot-assisted surgeries rely on accurate and real-time scene understanding to safely guide surgical instruments. However, segmentation models trained on static datasets face key limitations when deployed in these dynamic and evolving surgical environments. Class-incremental semantic segmentation (CISS) allows models to continually adapt to new classes while avoiding catastrophic forgetting of prior knowledge, without training on previous data. In this work, we build upon the recently introduced Taxonomy-Oriented Poincaré-regularized Incremental Class Segmentation (TOPICS) approach and propose an enhanced variant, termed TOPICS+, specifically tailored for robust segmentation of surgical scenes. Concretely, we incorporate the Dice loss into the hierarchical loss formulation to handle strong class imbalances, introduce hierarchical pseudo-labeling, and design tailored label taxonomies for robotic surgery environments. We also propose six novel CISS benchmarks designed for robotic surgery environments including multiple incremental steps and several semantic categories to emulate realistic class-incremental settings in surgical environments. In addition, we introduce a refined set of labels with more than 144 classes on the Syn-Mediverse synthetic dataset, hosted online as an evaluation benchmark. We make the code and trained models publicly available at http://topics.cs.uni-freiburg.de.

Rohit Mohan, Julia Hindel, Florian Drews et al.

Autonomous vehicles that navigate in open-world environments may encounter previously unseen object classes. However, most existing LiDAR panoptic segmentation models rely on closed-set assumptions, failing to detect unknown object instances. In this work, we propose ULOPS, an uncertainty-guided open-set panoptic segmentation framework that leverages Dirichlet-based evidential learning to model predictive uncertainty. Our architecture incorporates separate decoders for semantic segmentation with uncertainty estimation, embedding with prototype association, and instance center prediction. During inference, we leverage uncertainty estimates to identify and segment unknown instances. To strengthen the model's ability to differentiate between known and unknown objects, we introduce three uncertainty-driven loss functions. Uniform Evidence Loss to encourage high uncertainty in unknown regions. Adaptive Uncertainty Separation Loss ensures a consistent difference in uncertainty estimates between known and unknown objects at a global scale. Contrastive Uncertainty Loss refines this separation at the fine-grained level. To evaluate open-set performance, we extend benchmark settings on KITTI-360 and introduce a new open-set evaluation for nuScenes. Extensive experiments demonstrate that ULOPS consistently outperforms existing open-set LiDAR panoptic segmentation methods.

Borna Bešić, Nikhil Gosala, Daniele Cattaneo et al.

Scene understanding is a pivotal task for autonomous vehicles to safely navigate in the environment. Recent advances in deep learning enable accurate semantic reconstruction of the surroundings from LiDAR data. However, these models encounter a large domain gap while deploying them on vehicles equipped with different LiDAR setups which drastically decreases their performance. Fine-tuning the model for every new setup is infeasible due to the expensive and cumbersome process of recording and manually labeling new data. Unsupervised Domain Adaptation (UDA) techniques are thus essential to fill this domain gap and retain the performance of models on new sensor setups without the need for additional data labeling. In this paper, we propose AdaptLPS, a novel UDA approach for LiDAR panoptic segmentation that leverages task-specific knowledge and accounts for variation in the number of scan lines, mounting position, intensity distribution, and environmental conditions. We tackle the UDA task by employing two complementary domain adaptation strategies, data-based and model-based. While data-based adaptations reduce the domain gap by processing the raw LiDAR scans to resemble the scans in the target domain, model-based techniques guide the network in extracting features that are representative for both domains. Extensive evaluations on three pairs of real-world autonomous driving datasets demonstrate that AdaptLPS outperforms existing UDA approaches by up to 6.41 pp in terms of the PQ score.

Daniele Cattaneo, Matteo Vaghi, Abhinav Valada

Loop closure detection is an essential component of Simultaneous Localization and Mapping (SLAM) systems, which reduces the drift accumulated over time. Over the years, several deep learning approaches have been proposed to address this task, however their performance has been subpar compared to handcrafted techniques, especially while dealing with reverse loops. In this paper, we introduce the novel LCDNet that effectively detects loop closures in LiDAR point clouds by simultaneously identifying previously visited places and estimating the 6-DoF relative transformation between the current scan and the map. LCDNet is composed of a shared encoder, a place recognition head that extracts global descriptors, and a relative pose head that estimates the transformation between two point clouds. We introduce a novel relative pose head based on the unbalanced optimal transport theory that we implement in a differentiable manner to allow for end-to-end training. Extensive evaluations of LCDNet on multiple real-world autonomous driving datasets show that our approach outperforms state-of-the-art loop closure detection and point cloud registration techniques by a large margin, especially while dealing with reverse loops. Moreover, we integrate our proposed loop closure detection approach into a LiDAR SLAM library to provide a complete mapping system and demonstrate the generalization ability using different sensor setup in an unseen city.

Daniele Cattaneo, Domenico Giorgio Sorrenti, Abhinav Valada

Localization is a critically essential and crucial enabler of autonomous robots. While deep learning has made significant strides in many computer vision tasks, it is still yet to make a sizeable impact on improving capabilities of metric visual localization. One of the major hindrances has been the inability of existing Convolutional Neural Network (CNN)-based pose regression methods to generalize to previously unseen places. Our recently introduced CMRNet effectively addresses this limitation by enabling map independent monocular localization in LiDAR-maps. In this paper, we now take it a step further by introducing CMRNet++, which is a significantly more robust model that not only generalizes to new places effectively, but is also independent of the camera parameters. We enable this capability by combining deep learning with geometric techniques, and by moving the metric reasoning outside the learning process. In this way, the weights of the network are not tied to a specific camera. Extensive evaluations of CMRNet++ on three challenging autonomous driving datasets, i.e., KITTI, Argoverse, and Lyft5, show that CMRNet++ outperforms CMRNet as well as other baselines by a large margin. More importantly, for the first-time, we demonstrate the ability of a deep learning approach to accurately localize without any retraining or fine-tuning in a completely new environment and independent of the camera parameters.

Simone Fontana, Daniele Cattaneo, Augusto Luis Ballardini et al.

Point clouds registration is a fundamental step of many point clouds processing pipelines; however, most algorithms are tested on data that are collected ad-hoc and not shared with the research community. These data often cover only a very limited set of use cases; therefore, the results cannot be generalised. Public datasets proposed until now, taken individually, cover only a few kinds of environment and mostly a single sensor. For these reasons, we developed a benchmark, for localization and mapping applications, using multiple publicly available datasets. In this way, we are able to cover many kinds of environment and many kinds of sensor that can produce point clouds. Furthermore, the ground truth has been thoroughly inspected and evaluated to ensure its quality. For some of the datasets, the accuracy of the ground truth measuring system was not reported by the original authors, therefore we estimated it with our own novel method, based on an iterative registration algorithm. Along with the data, we provide a broad set of registration problems, chosen to cover different types of initial misalignment, various degrees of overlap, and different kinds of registration problems. Lastly, we propose a metric to measure the performances of registration algorithms: it combines the commonly used rotation and translation errors together, to allow an objective comparison of the alignments. This work aims at encouraging authors to use a public and shared benchmark, instead of data collected ad-hoc, to ensure objectivity and repeatability, two fundamental characteristics in any scientific field.

Augusto Luis Ballardini, Daniele Cattaneo, Rubén Izquierdo et al.

We present a probabilistic ego-lane estimation algorithm for highway-like scenarios that is designed to increase the accuracy of the ego-lane estimate, which can be obtained relying only on a noisy line detector and tracker. The contribution relies on a Hidden Markov Model (HMM) with a transient failure model. The proposed algorithm exploits the OpenStreetMap (or other cartographic services) road property lane number as the expected number of lanes and leverages consecutive, possibly incomplete, observations. The algorithm effectiveness is proven by employing different line detectors and showing we could achieve much more usable, i.e. stable and reliable, ego-lane estimates over more than 100 Km of highway scenarios, recorded both in Italy and Spain. Moreover, as we could not find a suitable dataset for a quantitative comparison with other approaches, we collected datasets and manually annotated the Ground Truth about the vehicle ego-lane. Such datasets are made publicly available for usage from the scientific community.

Daniele Cattaneo, Matteo Vaghi, Simone Fontana et al.

Global localization is an important and widely studied problem for many robotic applications. Place recognition approaches can be exploited to solve this task, e.g., in the autonomous driving field. While most vision-based approaches match an image w.r.t. an image database, global visual localization within LiDAR-maps remains fairly unexplored, even though the path toward high definition 3D maps, produced mainly from LiDARs, is clear. In this work we leverage Deep Neural Network (DNN) approaches to create a shared embedding space between images and LiDAR-maps, allowing for image to 3D-LiDAR place recognition. We trained a 2D and a 3D DNN that create embeddings, respectively from images and from point clouds, that are close to each other whether they refer to the same place. An extensive experimental activity is presented to assess the effectiveness of the approach w.r.t. different learning paradigms, network architectures, and loss functions. All the evaluations have been performed using the Oxford Robotcar Dataset, which encompasses a wide range of weather and light conditions.

Daniele Cattaneo, Matteo Vaghi, Augusto Luis Ballardini et al.

In this paper we present CMRNet, a realtime approach based on a Convolutional Neural Network to localize an RGB image of a scene in a map built from LiDAR data. Our network is not trained in the working area, i.e. CMRNet does not learn the map. Instead it learns to match an image to the map. We validate our approach on the KITTI dataset, processing each frame independently without any tracking procedure. CMRNet achieves 0.27m and 1.07deg median localization accuracy on the sequence 00 of the odometry dataset, starting from a rough pose estimate displaced up to 3.5m and 17deg. To the best of our knowledge this is the first CNN-based approach that learns to match images from a monocular camera to a given, preexisting 3D LiDAR-map.

Augusto L. Ballardini, Daniele Cattaneo, Domenico G. Sorrenti

In this report we present the work performed in order to build a dataset for benchmarking vision-based localization at intersections, i.e., a set of stereo video sequences taken from a road vehicle that is approaching an intersection, altogether with a reliable measure of the observer position. This report is meant to complement our paper "Vision-Based Localization at Intersections using Digital Maps" submitted to ICRA2019. It complements the paper because the paper uses the dataset, but it had no space for describing the work done to obtain it. Moreover, the dataset is of interest for all those tackling the task of online localization at intersections for road vehicles, e.g., for a quantitative comparison with the proposal in our submitted paper, and it is therefore appropriate to put the dataset description in a separate report. We considered all datasets from road vehicles that we could find as for the end of August 2018. After our evaluation, we kept only sub-sequences from the KITTI dataset. In the future we will increase the collection of sequences with data from our vehicle.