Searcharxiv⌕ Search

arXiv subjects

Tobias Fischer

Publications and source records attributed to Tobias Fischer.

At least 19 recordsLinked to original sources

Long-Term Multi-Session 3D Reconstruction Under Substantial Appearance Change

Long-term environmental monitoring requires the ability to reconstruct and align 3D models across repeated site visits separated by months or years to enable the detection of structural change and the assessment of ecosystem health. However, existing Structure-from-Motion (SfM) pipelines are generally designed for imagery captured within a limited time window and consequently fail in long-term monitoring scenarios such as repeated coral reef surveys with substantial visual and structural change. In this paper, we show that the primary limitation of current approaches lies in their inability to maintain visual correspondences under substantial temporal appearance change. We address this limitation by enforcing cross-session correspondences within a joint SfM reconstruction. Our approach combines handcrafted and learned visual features to establish correspondences across large temporal gaps, enabling the reconstruction of a single coherent 3D model from imagery captured years apart, where standard SfM fails to connect sessions. To ensure scalability and further improve alignment robustness on large datasets, we restrict expensive learned feature matching to a small set of likely cross-session image pairs identified via visual place recognition, which reduces computational cost while improving the reliability of cross-session correspondence establishment. We evaluate our method on long-term underwater datasets exhibiting significant real-world change, and demonstrate consistent joint reconstruction across sessions in cases where existing methods fail to connect the sessions or align them only coarsely.

cs.CV↗

Selective Sensor Acquisition for Multimodal Place Recognition

Multimodal Place Recognition (PR) can improve robustness, but most systems rigidly read and process every sensor for every query, even when the primary sensor is sufficient, with implications for energy consumption, second sensor update rate, and domain-specific considerations such as passive stealth. We introduce selective, controllable sensor acquisition, where a user specifies a desired second sensor usage rate and the system acquires the additional sensor only when the primary sensor's estimated performance is sufficiently poor. An online threshold adjustment achieves the requested usage rate by adapting to recent primary sensor performance, directing additional sensing towards queries where fusion is most likely to help without calibration specific to sensor modality, PR method, or environment. The approach requires only a PR method that produces a match score and applies to both single-frame and sequence-based PR. Our system, across multiple datasets, PR descriptors, and sensor combinations, recovers 55% of the available PR performance gain while using the second sensor on only 25% of queries, and 81% while using it on 50%. We further analyse alternative acquisition decision mechanisms and usage-rate control methods, and examine performance when the second sensor is stronger than, comparable to, or weaker than the primary sensor.

cs.RO↗

Why Domain Matters: Domain-Aware Benchmarking of Underwater Object Detection and Annotation Quality

Underwater object detection is strongly affected by domain shift, where performance can vary significantly across different locations, habitats, and deployment conditions. However, detector performance is typically evaluated using aggregate metrics that hide failures in specific environments, while existing domain generalization benchmarks often rely on synthetic variations that do not reflect real-world conditions. To address these limitations we introduce a framework that characterizes underwater images by appearance, scene composition, and acquisition geometry to assign domain labels. Using this framework, we perform the first systematic study of how domain factors influence both human annotation quality in underwater object detection datasets and deep learning-based detector performance, revealing substantial domain-dependent discrepancies. By incorporating physically meaningful domain labels, domain shift becomes something we can characterize, measure, benchmark, and act on. We highlight how our framework can be used to guide data collection and annotation, design more informative benchmarks, and assess detector robustness across diverse underwater environments.

cs.CV↗

Charged-current neutrino opacity within the relativistic Hartree-Fock framework for astrophysical simulations of core-collapse supernovae and binary neutron star mergers

Neutrinos and their weak interactions play a vital role in the physics of core-collapse supernovae and binary neutron star mergers. Their description within astrophysical simulations, including the weak rates, is of pivotal importance not only for the prediction of accurate neutrino fluxes and spectra, including the associated conditions relevant to nucleosynthesis, neutrinos are also responsible for heating and cooling of the stellar plasma as well as the transport of lepton number and entropy. In the present article, we develop an essential improvement of the description of the underlying nuclear medium, necessary for the calculations of charged-current weak rates, with the inclusion of explicitly momentum-dependent nuclear interactions. To this end, we introduce the relativistic Hartree-Fock (RHF) approach and the associated momentum-dependent nucleon self-energies. We discuss the resulting neutrino and antineutrino opacities and find large discrepancies comparing the weak rates at the RHF level with those of commonly used relativistic mean-field (RMF) models. In particular, we observe a substantial shift of previously reported large medium-dependent modifications associated with the RMF approach.

astro-ph.HE↗

Event-Based Visual Teach-and-Repeat via Fast Fourier-Domain Cross-Correlation

Visual teach-and-repeat (VT&R) navigation enables robots to autonomously traverse previously demonstrated paths using visual feedback. We present a novel event-camera-based VT&R system. Our system formulates event-stream matching as frequency-domain cross-correlation, transforming spatial convolutions into efficient Fourier-space multiplications. By exploiting the binary structure of event frames and applying image compression techniques, we achieve a processing latency of just 2.88 ms, about 3.5 times faster than conventional camera-based baselines that are optimised for runtime efficiency. Experiments using a Prophesee EVK4 HD event camera mounted on an AgileX Scout Mini robot demonstrate successful autonomous navigation across 3000+ meters of indoor and outdoor trajectories in daytime and nighttime conditions. Our system maintains Cross-Track Errors (XTE) below 15 cm, demonstrating the practical viability of event-based perception for real-time VT&R navigation.

cs.RO↗

Removing the Compute Bottleneck for Event-based Visual Place Recognition with Spiking Neural Networks

Neuromorphic sensing and computing promise low latency and high energy efficiency for robotics, yet most event-based visual place recognition (VPR) pipelines reintroduce dense, frame-like computation downstream of an inherently sparse sensor, forfeiting the sensor's latency advantage. In this paper, we address the problem of resolving an event-based VPR query in tens of microseconds on a commodity CPU. We train a two-layer spiking neural network (SNN) with additive spike-timing-dependent plasticity (STDP), which drives the learned weight matrix towards a strongly bimodal distribution, amenable to aggressive magnitude pruning. At inference, our pipeline exploits this sparsity by reading only the pruned weights corresponding to the query's active pixels. As surviving weights share a near-uniform magnitude, each neuron's score reduces to an integer count of matching synapses instead of a weighted sum, lowering per-query latency. This computation is small enough to remain resident in a CPU's fast on-chip cache. On three event-based VPR benchmarks, our sparse SNN exceeds the recall of LENS, an existing event-based SNN, while reducing per-query latency by 5.5-6.2x to tens of microseconds. It matches the recall of a dense variant of our network and of the sum-of-absolute-differences (SAD) baseline, while reading 10x fewer weights than the dense variant. We further characterise how recall and latency scale with the number of active pixels and reference places. These results suggest that the sparsity of both event-based input and learned weights can already be exploited for low-latency inference on conventional processors.

cs.CV↗

Image-Space Refraction Correction for Underwater 3D Reconstruction: Warping Flat-Port Views into Pinhole Perspective

Consumer-grade cameras in flat-port housings are widely used for underwater exploration and mapping of coral reefs and seafloor habitats due to their low cost and accessibility. However, refraction at flat-port interfaces causes bowl-shaped deformation in reconstructed scenes and camera trajectories, compromising the metric accuracy required for mapping and navigation. To remove the dominant refractive distortion before reconstruction, we introduce a physics-based refraction correction in image space. Our method is downstream-agnostic: the refraction-corrected images can be directly used as input to existing reconstruction and SLAM algorithms. We characterize the refractive distortion through ray-tracing simulations and validate our correction on two real underwater datasets with differing scene structures. Compared with conventional and refractive Structure-from-Motion (SfM), our approach removes reconstruction deformation while registering more frames and maintaining low reprojection error. The correction further generalizes across diverse reconstruction and VSLAM backends, demonstrating its broad applicability to downstream vision pipelines.

cs.CV↗

Coral Grow-out Robotic Assessment System (CGRAS): Scaling Coral Recruit Monitoring Through Robotics and Computer Vision

Climate change is the largest threat to coral reefs, with increasing global impacts accelerating the need for scalable reef restoration technologies. Large-scale reef restoration depends on the mass production of corals, such as through coral aquaculture. Coral seeding with recruits grown in aquaculture facilities is a feasible restoration approach, but effective production requires consistent, high-frequency monitoring of tens of thousands of macroscopic (0.5-2mm diameter) recruits, making conventional manual assessment prohibitively labor-intensive. To address this monitoring bottleneck, we introduce the Coral Grow-out Robotic Assessment System (CGRAS) which combines robotic imaging and computer vision to automate data acquisition, perform multi-species detection and counting of corals, and evaluate coral health. CGRAS automatically extracts coral growth, survival and spatial distribution metrics, with the aim of providing timely feedback to operators for optimizing production, grow-out and deployment workflow processes. We demonstrate CGRAS in a large aquaculture facility on standardized coral settlement tiles, reducing the time and labor costs by a factor of 9.6 as compared to manual monitoring, whilst achieving 96.4% agreement for Acropora kenti corals relative to expert counts.

cs.RO↗

AI-driven Dispensing of Coral Reseeding Devices for Broad-scale Restoration of the Great Barrier Reef

Coral reefs are on the brink of collapse, with climate change, ocean acidification, and pollution leading to a projected 70-90% loss of coral species within the next decade. Reef restoration is crucial, but its success hinges on introducing automation to upscale efforts. In this work, we present a highly configurable AI pipeline for the real-time deployment of coral reseeding devices. The pipeline consists of three core components: (i) the image labeling scheme, designed to address data availability and reduce the cost of expert labeling; (ii) the classifier which performs automated analysis of underwater imagery, at the image or patch-level, while also enabling quantitative coral coverage estimation; and (iii) the decision-making module that determines whether deployment should occur based on the classifier's analysis. By reducing reliance on manual experts, our proposed pipeline increases operational range and efficiency of reef restoration. We validate the proposed pipeline at five sites across the Great Barrier Reef, benchmarking its performance against annotations from expert marine scientists. The pipeline achieves 77.8% deployment accuracy, 89.1% accuracy for sub-image patch classification, and real-time model inference at 5.5 frames per second on a Jetson Orin. To address the limited availability of labeled data in this domain and encourage further research, we publicly release a comprehensive, annotated dataset of substrate imagery from the surveyed sites.

cs.CV↗

EventGeM: Global-to-Local Feature Matching for Event-Based Visual Place Recognition

Event cameras are rapidly rising in popularity for robotic and computer vision tasks because their sparse activation delivers energy-efficient, high-dynamic-range, and fast sensing. Event cameras have been used in robotic navigation and localization tasks where positioning must occur in real time with sufficient accuracy. However, current event-based localization methods suffer from poor spatial understanding and are not viewpoint tolerant. In this paper, we address the problem of viewpoint-robust place recognition directly from event streams. We present EventGeM, a global-to-local feature fusion pipeline for event-based visual place recognition that combines whole-image feature detection to shortlist top candidates for 2D homography-based re-ranking with random sample consensus (RANSAC). We also contribute a regional generalized mean pooling (GeM) layer that learns to return the most relevant spatial features using per-row exponents to pool event streams into a compact global descriptor, trained on the NYC-Event-VPR dataset. These contributions overcome shortfalls in currently available event-based localization methods that fail to recognize similar places with large changes in viewpoint. To evaluate viewpoint-robust localization, we contribute a new event-based dataset that includes repeated traverses with a severe lateral shift. EventGeM improves absolute Recall@1 by 7 to 43 percentage points over the strongest baseline in each experiment. We also deploy EventGeM on a robotic platform, demonstrating real-time performance of our hierarchical pipeline. The code for EventGeM is available at https://github.com/AdamDHines/Event-GeM.

cs.CV↗

Multi-viewpoint Geo-localization with Event Cameras

Robot localization is an ongoing challenge that demands mapping and positioning systems that are tolerant to viewpoint change. Event cameras are attracting increasing interest and adoption in robotics; however, dealing with viewpoint variance is an under-investigated problem in existing event-based localizers. In addition, event-based datasets that emphasize viewpoint variance for challenging localization situations are scarce. Here, we introduce an event-based visual place recognition (VPR) system that performs robustly under viewpoint changes. We converted five large-scale geo-tagged datasets, conventionally used to train frame-based localization systems, into synthetic event streams using Image-to-Event (I2E) conversion, and used them to fine-tune a pre-trained event-based vision transformer backbone with a multi-loss function, yielding a system we call MegaEvent that learns viewpoint-robust features for place recognition. We achieved an average Recall@1 of 82% across three existing event-based localization datasets, leading the next best event-based method by 20 recall points, and frame-based VPR models applied directly to event frames by 8 to 26 recall points. We introduce a new, challenging dataset - Springfield-Event-VPR - which features a 3.7km walking route recorded in three camera orientations for a total of 11.1km, which MegaEvent outperforms the strongest baseline by 9 recall points. The code for MegaEvent is available at https://github.com/AdamDHines/megaevent.

cs.CV↗

The EventCV Library for Event-Based Robotic Vision

Event cameras detect per-pixel brightness changes asynchronously on microsecond timescales, with high dynamic range and low power draw. These are desirable properties for robots that move fast or work in difficult lighting conditions. However, integrating an event camera into a real-world robotic pipeline still requires substantial effort: plug-and-play drivers do not exist, event streams are recorded in a variety of incompatible file formats, and most projects rely on custom research-grade code. Here, we present EventCV, an open-source and extensible Rust library with OpenCV-style Python bindings that lowers the entry barrier to working with event cameras. EventCV provides a wide range of features: denoising filters and geometric transforms, augmentations, corner detection and unsupervised feature learning, contrast-maximization motion estimation, a video-to-events simulator, and Open Neural Network Exchange (ONNX) inference for deployment in robotic stacks. EventCV integrates the Neuromorphic Drivers package, allowing an event camera stream to be processed directly in real time. No existing toolkit covers this range of operations in one package, and EventCV builds representations and decodes files 1.1x to 3.7x faster than the currently available libraries. We deploy EventCV on a Jetson Orin AGX and present three robotics case studies spanning object detection, on-device model inference, and localization. Project webpage: https://eventcv.net.

cs.RO↗

Learning the Shoreline: A Very High-Resolution Approach to Reef Island Dynamics

Pacific atoll islets are often described as stable in global-scale studies, typically based on long-term shoreline proxies such as vegetation line or morphometrics like planform surface area. While informative, these approaches can obscure short-term, localized coastal dynamics -including changes in island shape and position -that are critical for ecosystem function, cultural practices, and coastal infrastructure resilience. This study presents a transferable, automated approach to shoreline monitoring using very high-resolution Pl{é}iades imagery and a XGBoost classifier. The method integrates spectral indices and textural features to delineate the outer limit of emerged land, including vegetated areas, beaches, man-made surfaces, and beach rock. This shoreline definition supports finescale, spatially explicit monitoring of reef island dynamics, even in morphologically complex environments. Developed and tested on multiple atolls in French Polynesia (Tetiaroa, Tikehau, Hao, and Puka Puka), the model achieves high accuracy (mean Intersection over Union $\approx$ 0.99; Mean Absolute Positional Error $\approx$ 1.28 m) and demonstrates strong performance on both training and held-out sites, validating its spatial transferability. The extracted shorelines reveal subtle but significant island-scale changes in extent, configuration, and spatial position that remain undetected by conventional shoreline proxies and surface metrics. By enabling highprecision, scalable shoreline monitoring, this method provides a more nuanced understanding of atoll change processes. It supports Pacific efforts to move beyond narratives of passive loss toward frameworks of resilience and adaptation, while providing spatial tools tailored to low-lying island realities.

eess.IV↗

Automatic Map Density Selection for Locally-Performant Visual Place Recognition

A key challenge in translating Visual Place Recognition (VPR) from the lab to long-term deployment is ensuring a priori that a system can meet user-specified performance requirements across different parts of an environment, rather than just on average globally. One critical mechanism for controlling this local performance is the density of the reference mapping database, yet this factor is largely neglected in existing work, where fixed, engineering-driven sampling densities based on sensors, storage, or GPS frequency are typically used. In this paper, we propose a VPR mapping approach that uses two reference traverses from the operating environment to automatically select an appropriate map density satisfying two user-defined requirements: (1) a target Local Recall@1 level, and (2) the proportion of the operational environment over which it must be met or exceeded, which we term the Recall Achievement Rate (RAR). Our approach uses spatial consistency and coherence features from reference-to-reference matches at multiple map densities to estimate the density needed to meet these targets on unseen deployment data. Through experiments across two VPR methods and the Nordland and Oxford RobotCar benchmarks, we show that our system consistently meets or exceeds the target Local Recall@1 over at least the user-specified proportion of the environment. Comparisons with alternative baselines show that it reliably selects an appropriate operating point in map density, avoiding unnecessarily dense maps. Finally, ablations evaluate sensitivity to reference traversal choice and segment length, and our analysis reveals that conventional global Recall@1 is a poor predictor of the often more operationally meaningful RAR metric.

cs.CV↗

Quantile Transfer for Reliable Operating Point Selection in Visual Place Recognition

Visual Place Recognition (VPR) is a key component for localization in Global Navigation Satellite System (GNSS)-denied environments, but its performance critically depends on selecting an image matching threshold (operating point) that balances precision and recall. Thresholds are typically hand-tuned offline for a specific environment and fixed during deployment, leading to degraded performance under environmental change. We propose a method that automatically estimates the operating point of a VPR system to maximize recall whilst aiming to achieve 100% precision. The method uses a small calibration traversal with known correspondences and transfers thresholds to deployment via quantile normalization of similarity score distributions. This quantile transfer ensures that thresholds remain stable across calibration sizes and query subsets. Experiments with seven state-of-the-art VPR techniques across five benchmark datasets demonstrate that our proposed approach consistently outperforms existing baselines, enabling the underlying VPR technique to operate at 100% precision in approximately twice as many deployment scenarios (median improvement), while retrieving up to 29% more correct matches at that precision. The method eliminates manual tuning by adapting to new environments and generalizing across operating conditions. Our code is available at https://github.com/DhyeyR-007/Quantile-Transfer-for-Reliable-VPR.

cs.RO↗

Circular polarization of gravitational waves from magnetorotational supernovae

Context. Gravitational waves (GWs) provide a unique probe of the explosion mechanism of massive stars and the evolution of nascent proto-neutron stars (PNSs). Magnetorotational explosions are one of the promising noncanonical core-collapse supernova scenarios, possibly linked to magnetar formation and energetic supernova explosions. However, the GW signatures of such events remain incompletely understood. Aims. We investigate the origin and nature of GW polarization arising from a magnetorotational core-collapse model and examine its potential detectability by current GW observatories. Methods. We performed a 3D GRMHD simulation of a rapidly rotating, strongly magnetized 20 $M_{\odot}$ progenitor, including multi-energy neutrino transport. The GW signals were extracted using the standard quadrupole formalism, and their polarization states were analyzed with Stokes parameters. Results. Strong circular polarization emerges along the rotation axis during the early post-bounce phase ($\lesssim$ 230 ms). The characteristic GW spectrum peaks at ~90 Hz, consistent with the emission at twice the local angular velocity (~45 Hz) around the PNS surface at cylindrical radii of ~50 km. These features are attributed to the low-$T/\vert{}W\vert{}$ instabilities and nonaxisymmetric motions near the PNS and not to the MHD jets themselves. The polarization signals lie within the sensitivity bands of current detectors such as Advanced LIGO, Advanced Virgo, and KAGRA. Conclusions. Models launching magnetorotationally driven jets can produce circularly polarized GW signals originating from the inner PNS region. This provides an observational signature that complements previous findings from nonmagnetized rotating models. Thus, GW polarization is a promising diagnostic of noncanonical core-collapse supernovae. Future third-generation detectors will be crucial to fully exploit this potential.

astro-ph.HE↗

ReMoSPLAT: Reactive Mobile Manipulation Control on a Gaussian Splat

Reactive control can gracefully coordinate the motion of the base and the arm of a mobile manipulator. However, incorporating an accurate representation of the environment to avoid obstacles without involving costly planning remains a challenge. In this work, we present ReMoSPLAT, a reactive controller based on a quadratic program formulation for mobile manipulation that leverages a Gaussian Splat representation for collision avoidance. By integrating additional constraints and costs into the optimisation formulation, a mobile manipulator platform can reach its intended end effector pose while avoiding obstacles, even in cluttered scenes. We investigate the trade-offs of two methods for efficiently calculating robot-obstacle distances, comparing a purely geometric approach with a rasterisation-based approach. Our simulation experiments on both synthetic and real-world scans demonstrate the feasibility of the proposed method, achieving performance comparable to controllers that rely on perfect ground-truth information. We further validate the approach on a real robot platform more details: https://remosplat.github.io

cs.RO↗

Strongly interacting matter with criticality induced by modified excluded volume in core-collapse supernova simulations

This article reviews critically the core-collapse supernova explosion mechanism associated with a sufficiently strong first-order phase transition from normal nuclear, in general hadronic matter to deconfined quark matter, which commonly assumes Gibbs conditions for the coexistence of phases and a phase transition construction accordingly. To this end, a novel class of multi-purpose equation of state (EOS) is developed, based on the modified excluded volume (MEV) approach employing a medium-dependent excluded-volume functional within the relativistic mean field framework with density-dependent meson-nucleon couplings. The chosen MEV parametrisation features the change in the number of degrees of freedom, mimicking the EOS softening in excess of nuclear saturation density, featuring a first-order phase transition with van der Waals like behaviour and the presence of a critical point at high temperatures. Simulations of core-collapse supernovae are performed, based on general relativistic neutrino radiation hydrodynamics in spherical symmetry, in order to explore the previously reported supernova explosion scenario within this class of phenomenological modified microscopic hadronic EOS. A burst-like neutrino signature is released, substantially longer than previously reported based on common hadron-quark hybrid model EOS with two-phase approach and Gibbs phase-transition construction, as observable signal, which is complemented by a gravitational wave mode analysis.

astro-ph.HE↗