Search

Zero-shot object pose estimation enables the retrieval of object poses from images without necessitating object-specific training. In recent approaches this is facilitated by vision foundation models (VFM), which are pre-trained models that are effectively general-purpose feature extractors. The characteristics exhibited by these VFMs vary depending on the training data, network architecture, and training paradigm. The prevailing choice in this field are self-supervised Vision Transformers (ViT). This study assesses the influence of Latent Diffusion Model (LDM) backbones on zero-shot pose estimation. In order to facilitate a comparison between the two families of models on a common ground we adopt and modify a recent approach. Therefore, a template-based multi-staged method for estimating poses in a zero-shot fashion using LDMs is presented. The efficacy of the proposed approach is empirically evaluated on three standard datasets for object-specific 6DoF pose estimation. The experiments demonstrate an Average Recall improvement of up to 27% over the ViT baseline. The source code is available at: https://github.com/BvG1993/DZOP.

We study the convergence of two of the most widely used and intuitive approaches for computing the spectra of differential operators with quasiperiodic coefficients: the supercell method and the superspace method. In both cases, Floquet-Bloch theory for periodic operators can be used to compute approximations to the spectrum. We illustrate our results with examples of Schr\"odinger and Helmholtz operators.

Meningeal lymphatic vessels (MLVs) are responsible for the drainage of waste products from the human brain. An impairment in their functionality has been associated with aging as well as brain disorders like multiple sclerosis and Alzheimer's disease. However, MLVs have only recently been described for the first time in magnetic resonance imaging (MRI), and their ramified structure renders manual segmentation particularly difficult. Further, as there is no consistent notion of their appearance, human-annotated MLV structures contain a high inter-rater variability that most automatic segmentation methods cannot take into account. In this work, we propose a new rater-aware training scheme for the popular nnU-Net model, and we explore rater-based ensembling strategies for accurate and consistent segmentation of MLVs. This enables us to boost nnU-Net's performance while obtaining explicit predictions in different annotation styles and a rater-based uncertainty estimation. Our final model, MLV$^2$-Net, achieves a Dice similarity coefficient of 0.806 with respect to the human reference standard. The model further matches the human inter-rater reliability and replicates age-related associations with MLV volume., Comment: ML4H 2024

The eROSITA instrument on board Spectrum-Roentgen-Gamma has completed four scans of the X-ray sky, leading to the detection of almost one million X-ray sources in eRASS1 only, including multiple new X-ray binary candidates. We report on analysis of the X-ray binary 1eRASS J085039.9-421151, using a ~55\,ks long NuSTAR observation, following its detection in each eROSITA scan. Analysis of the eROSITA and NuSTAR X-ray spectra in combination with X-shooter data of the optical counterpart provide evidence of an X-ray binary with a red supergiant (RSG) companion, confirming previous results, although we determine a cooler spectral type of M2-3, owing to the presence of TiO bands in the optical and near infrared spectra. The X-ray spectrum is well-described by an absorbed power law with a high energy cutoff typically applied for accreting high mass X-ray binaries. In addition, we detect a strong fluorescent neutral iron line with an equivalent width of ~700\,eV and an absorption edge, the latter indicating strong absorption by a partial covering component. It is unclear if the partial absorber is ionised. There is no significant evidence of a cyclotron resonant scattering feature. We do not detect any pulsations in the NuSTAR lightcurves, possibly on account of a large spin period that goes undetected due to insufficient statistics at low frequencies or potentially large absorption that causes pulsations to be smeared out. Even so, the low persistent luminosity, the spectral parameters observed (photon index, $\Gamma<1.0$), and the minuscule likelihood of detection of RSG-black hole systems, suggest that the compact object is a neutron star., Comment: 17 pages, 11 figures, accepted by A&A

This contribution is dedicated to the exploration of exponential operator splitting methods for the time integration of evolution equations. It entails the review of previous achievements as well as the depiction of novel results. The standard class of splitting methods involving real coefficients is contrasted with an alternative approach that relies on the incorporation of complex coefficients. In view of long-term computations for linear evolution equations, it is expedient to distinguish symmetric, symmetric-conjugate, and alternating-conjugate schemes. The scope of applications comprises high-order reaction-diffusion equations and complex Ginzburg-Landau equations, which are of relevance in the theories of patterns and superconductivity. Time-dependent Gross-Pitaevskii equations and their parabolic counterparts, which model the dynamics of Bose-Einstein condensates and arise in ground state computations, are formally included as special cases. Numerical experiments confirm the validity of theoretical stability conditions and global error bounds as well as the benefits of higher-order complex splitting methods in comparison with standard schemes.

XTE J1829-098 is a transient X-ray pulsar with a period of ~7.8 s. It is a candidate Be star system, although the evidence for this is not yet definitive. We investigated the twenty-year long X-ray light curve using the Rossi X-ray Timing Explorer Proportional Counter Array (PCA), Neil Gehrels Swift Observatory Burst Alert Telescope (BAT), and the Monitor of All-sky X-ray Image (MAXI). We find that all three light curves are clearly modulated on the ~244 day orbital period previously reported from PCA monitoring observations, with outbursts confined to a narrow phase range. The light curves also show that XTE J1829-098 was in an inactive state between approximately December 2008 and April 2018 and no strong outbursts occurred. Such behavior is typical of Be X-ray binary systems, with the absence of outbursts likely related to the dissipation of the Be star's decretion disk. The mean outburst shapes can be approximated with a triangular profile and, from a joint fit of this to all three light curves, we refine the orbital period to 243.95 +/- 0.04 days. The mean outburst profile does not show any asymmetry and has a total phase duration of 0.140 +/- 0.007. However, the PCA light curve shows that there is considerable cycle-to-cycle variability of the individual outbursts. We compare the properties of XTE J1829-098 with other sources that show short phase-duration outbursts, in particular GS 1843-02 (2S 1845-024) which has a very similar orbital period, but longer pulse period, and whose orbit is known to be highly eccentric., Comment: Accepted for publication in the Astrophysical Journal. 21 pages

Robots are increasingly envisioned to interact in real-world scenarios, where they must continuously adapt to new situations. To detect and grasp novel objects, zero-shot pose estimators determine poses without prior knowledge. Recently, vision language models (VLMs) have shown considerable advances in robotics applications by establishing an understanding between language input and image input. In our work, we take advantage of VLMs zero-shot capabilities and translate this ability to 6D object pose estimation. We propose a novel framework for promptable zero-shot 6D object pose estimation using language embeddings. The idea is to derive a coarse location of an object based on the relevancy map of a language-embedded NeRF reconstruction and to compute the pose estimate with a point cloud registration method. Additionally, we provide an analysis of LERF's suitability for open-set object pose estimation. We examine hyperparameters, such as activation thresholds for relevancy maps and investigate the zero-shot capabilities on an instance- and category-level. Furthermore, we plan to conduct robotic grasping experiments in a real-world setting.

This guide is for everyone who seeks advice for creating stable, secure, and persistent Uniform Resource Identifiers (URIs) in order to publish their data in accordance to the FAIR principles. The use case does not matter. It could range from publishing the results of a small research project to a large knowledge graph at a big corporation. The FAIR principles apply equally and this is why it is important to put extra thought into the URI selection process. The title aims to extend the tradition of "Cool URIs don't change" and "Cool URIs for the Semantic Web". Much has changed since the publication of these works and we would like to revisit some of the principles. Many still hold today, some had to be reworked, and we could also identify new ones

Soft gamma-ray emission (100 keV -- 10 MeV) has previously been detected in the hard state of several microquasars. In some sources, this emission was found to be highly polarized and was suggested to be emitted at the base of the jet. Until now, no $\gamma$-ray polarization had been found in any other state. Using INTEGRAL/IBIS, we studied the soft gamma-ray spectral and polarization properties of Swift J1727.8-1613 throughout its outburst. We detect a highly polarized spectral component in both the hard intermediate state and the early stages of the soft intermediate state above 210 keV. In the hard intermediate state, the polarization angle significantly deviates from the compact jet angle projected onto the sky, whereas in the soft intermediate they are closely aligned. This constitutes the first detection of jet-aligned polarization in the soft gamma-ray for a microquasar. We attribute this polarized spectral component to synchrotron emission from the jet, which indicates that some of the jet might persist into the softer states., Comment: 7 pages, 4 figures. Accepted for publication in A&A Letters

Robotic search and rescue (SAR) supports response teams by accelerating disaster assessment and by keeping operators away from hazardous environments. In the event of a chemical, biological, radiological, and nuclear (CBRN) disaster, robots are deployed to identify and locate radiation sources. Human responders then assess the situation and neutralize the danger. The presented system takes a step toward enhanced integration of robots into SAR teams. Integrating autonomous radiation mapping with semi-autonomous substance sampling and online analysis of the CBRN threat lets the human operator localize and assess the threat from a safe distance. Two LiDARs, an IMU, and a Geiger counter are used for mapping the surrounding area and localizing potential radiation sources. A mobile manipulator with six Degrees of Freedom manipulates valves and samples substances that are analyzed by an onboard Raman spectrometer. The human operator monitors the mission's progression from a remote location defining target locations and directing the semi-autonomous manipulation processes. Diverse recovery behaviours aid robot deployment, system state monitoring, as well as recovery of hard- and software. Field tests showcase the capabilities of the presented system during trials at the CBRN disaster response challenge European Robotics Hackathon (EnRicH). We provide recorded sensor data and implemented software through a GitHub repository: https://github.com/TW-Robotics/search-and-rescue-robot-2024.

In 2021, the high-mass X-ray binary EXO 2030+375 underwent a giant X-ray outburst, the first since 2006, that reached a peak flux of ${\sim}600\,\mathrm{mCrab}$ (3-50\,keV). The goal of this work is to study the spectral evolution over the course of the outburst, search for possible cyclotron resonance scattering features (CRSFs), and to associate spectral components with the emission pattern of the accretion column. We used broadband spectra taken with the Nuclear Spectroscopic Telescope Array (NuSTAR), the Neutron Star Interior Composition Explorer (NICER), and Chandra near the peak and during the decline phase of the outburst. We describe the data with established empirical continuum models and perform pulse-phase-resolved spectroscopy. We compare the spectral evolution with pulse phase using a proposed geometrical emission model. We find a significant spectral hardening toward lower luminosity, a behavior that is expected for super-critical sources. The continuum shape and evolution cannot be described by a simple power-law model with exponential cutoff; it requires additional absorption or emission components. We can confirm the presence of a narrow absorption feature at ${\sim}10\,\mathrm{keV}$ in both NuSTAR observations. The absence of harmonics puts into question the interpretation of this feature as a CRSF. The empirical spectral components cannot be directly associated with identified emission components from the accretion column., Comment: 12 pages, 8 figures, accepted in A&A

The Be X-ray binary EXO 2030+375 went through its third recorded giant outburst from June 2021 to early 2022. We present the results of both spectral and timing analysis based on NICER monitoring, covering the 2-10 keV flux range from 20 to 310 mCrab. Dense monitoring with observations carried out about every second day and a total exposure time of 160 ks allowed us to closely track the source evolution over the outburst. Changes in spectral shape and pulse profiles showed a stable luminosity dependence during the rise and decline. The same type of dependence has been seen in past outbursts. The pulse profile is characterized by several distinct peaks and dips. The profiles show a clear dependence on luminosity with a stark transition at a luminosity of 2x10^36 erg/s, indicating a change in the emission pattern. Using relativistic ray-tracing, we demonstrate how anisotropic beaming of emission from an accretion channel with constant geometrical configuration can give rise to the observed pulse profiles over a range of luminosities., Comment: 15 pages, 16 figures, accepted by A&A

The Neutron Star Interior Composition Explorer (NICER) monitoring campaign of Cyg X-1 allows us to study its spectral-timing behavior at energies ${<}1$ keV across all states. The hard state power spectrum can be decomposed into two main broad Lorentzians with a transition at around 1 Hz. The lower-frequency Lorentzian is the dominant component at low energies. The higher-frequency Lorentzian begins to contribute significantly to the variability above 1.5 keV and dominates at high energies. We show that the low- and high-frequency Lorentzians likely represent individual physical processes. The lower-frequency Lorentzian can be associated with a (possibly Comptonized) disk component, while the higher-frequency Lorentzian is clearly associated with the Comptonizing plasma. At the transition of these components, we discover a low-energy timing phenomenon characterized by an abrupt lag change of hard (${\gtrsim}2$ keV) with respect to soft (${\lesssim}1.5$ keV) photons, accompanied by a drop in coherence, and a reduction in amplitude of the second broad Lorentzian. The frequency of the phenomenon increases with the frequencies of the Lorentzians as the source softens and cannot be seen when the power spectrum is single-humped. A comparison to transient low-mass X-ray binaries shows that this feature does not only appear in Cyg X-1, but that it is a general property of accreting black hole binaries. In Cyg X-1, we find that the variability at low and high energies is overall highly coherent in the hard and intermediate states. The high coherence shows that there is a process at work which links the variability, suggesting a physical connection between the accretion disk and Comptonizing plasma. This process fundamentally changes in the soft state, where strong red noise at high energies is incoherent to the variability at low energies., Comment: 18+29 pages, 17+54 figures, accepted for publication in Astronomy & Astrophysics

Context. The High-Mass X-ray Binary (HMXB) system GX 301$-$2 is a persistent source with a well-known variable cyclotron line centered at 35 keV. Recently, a second cyclotron line at 50 keV has been reported with a presumably different behavior than the 35 keV line. Aims. We investigate the presence of the newly discovered cyclotron line in the phase-averaged and phase-resolved spectra at higher luminosities than before. We further aim to determine the pulse-phase variability of both lines. Methods. We analyze a NuSTAR observation of GX 301$-$2 covering the pre-periastron flare, where the source luminosity reached its peak of ${\sim} 4 \times 10^{37}\,\mathrm{erg}\,\mathrm{s}^{-1}$ in the 5-50 keV range. We analyze the phase-averaged spectra in the NuSTAR energy range from 3.5-79 keV for both the complete observation and three time segments of it. We further analyze the phase-resolved spectra and the pulse-phase variability of continuum and cyclotron line parameters. Results. We confirm that the description of the phase-averaged spectrum requires a second absorption feature at $51.5^{+1.1}_{-1.0}$ keV besides the established line at 35 keV. The statistical significance of this feature in the phase-averaged spectrum is $>99.999\%$. We further find that the 50 keV cyclotron line is present in three of eight phase bins. Conclusions. Based on the results of our analysis, we confirm that the detected absorption feature is very likely to be a cyclotron line. We discuss a variety of physical scenarios which could explain the proposed anharmonicity, but also outline circumstances under which the lines are harmonically related. We further present the cyclotron line history of GX 301$-$2 and evaluate concordance among each other. We also discuss an alternative spectral model including cyclotron line emission wings., Comment: accepted for publication in Astronomy & Astrophysics, 20 pages, 16 figures

Estimating 2D-3D correspondences between RGB images and 3D space is a fundamental problem in 6D object pose estimation. Recent pose estimators use dense correspondence maps and Point-to-Point algorithms to estimate object poses. The accuracy of pose estimation depends heavily on the quality of the dense correspondence maps and their ability to withstand occlusion, clutter, and challenging material properties. Currently, dense correspondence maps are estimated using image-to-image translation models based on GANs, Autoencoders, or direct regression models. However, recent advancements in image-to-image translation have led to diffusion models being the superior choice when evaluated on benchmarking datasets. In this study, we compare image-to-image translation networks based on GANs and diffusion models for the downstream task of 6D object pose estimation. Our results demonstrate that the diffusion-based image-to-image translation model outperforms the GAN, revealing potential for further improvements in 6D object pose estimation models., Comment: Submitted to the First Austrian Symposium on AI, Robotics, and Vision 2024

Recent advances in machine learning have greatly benefited object detection and 6D pose estimation. However, textureless and metallic objects still pose a significant challenge due to few visual cues and the texture bias of CNNs. To address his issue, we propose a strategy for inducing a shape bias to CNN training. In particular, by randomizing textures applied to object surfaces during data rendering, we create training data without consistent textural cues. This methodology allows for seamless integration into existing data rendering engines, and results in negligible computational overhead for data rendering and network training. Our findings demonstrate that the shape bias we induce via randomized texturing, improves over existing approaches using style transfer. We evaluate with three detectors and two pose estimators. For the most recent object detector and for pose estimation in general, estimation accuracy improves for textureless and metallic objects. Additionally we show that our approach increases the pose estimation accuracy in the presence of image noise and strong illumination changes. Code and datasets are publicly available at github.com/hoenigpeter/randomized_texturing.

When applying Hamiltonian operator splitting methods for the time integration of multi-species Vlasov-Maxwell-Landau systems, the reliable and efficient numerical approximation of the Landau equation represents a fundamental component of the entire algorithm. Substantial computational issues arise from the treatment of the physically most relevant three-dimensional case with Coulomb interaction. This work is concerned with the introduction and numerical comparison of novel approaches for the evaluation of the Landau collision operator. In the spirit of collocation, common tools are the identification of fundamental integrals, series expansions of the integral kernel and the density function on the main part of the velocity domain, and interpolation as well as quadrature approximation nearby the singularity of the kernel. Focusing on the favourable choice of the Fourier spectral method, their practical implementation uses the reduction to basic integrals, fast Fourier techniques, and summations along certain directions. Moreover, an important observation is that a significant percentage of the overall computational effort can be transferred to precomputations which are independent of the density function. For the purpose of exposition and numerical validation, the cases of constant, regular, and singular integral kernels are distinguished, and the procedure is adapted accordingly to the increasing complexity of the problem. With regard to the time integration of the Landau equation, the most expedient approach is applied in such a manner that the conservation of mass is ensured.

We establish new results on the spectra and pseudo-spectra of tridiagonal $k$-Toeplitz operators and matrices. In particular, we prove the connection between the winding number of the eigenvalues of the symbol function and the exponential decay of the associated eigenvectors (or pseudo-eigenvectors). Our results elucidate the topological origin of the non-Hermitian skin effect in general one-dimensional polymer systems of subwavelength resonators with imaginary gauge potentials, proving the observation and conjecture in arXiv:2307.13551. We also numerically verify our theory for these systems., Comment: 18 pages, 6 figures

The present work provides a comprehensive study of symmetric-conjugate operator splitting methods in the context of linear parabolic problems and demonstrates their additional benefits compared to symmetric splitting methods. Relevant applications include nonreversible systems and ground state computations for linear Schr\"odinger equations based on the imaginary time propagation. Numerical examples confirm the favourable error behaviour of higher-order symmetric-conjugate splitting methods and illustrate the usefulness of a time stepsize control, where the local error estimation relies on the computation of the imaginary parts and thus requires negligible costs., Comment: Paper to be published in Journal of Computational Dynamics

The present work is concerned with the extension of modified potential operator splitting methods to specific classes of nonlinear evolution equations. The considered partial differential equations of Schr{\"o}dinger and parabolic type comprise the Laplacian, a potential acting as multiplication operator, and a cubic nonlinearity. Moreover, an invariance principle is deduced that has a significant impact on the efficient realisation of the resulting modified operator splitting methods for the Schr{\"o}dinger case.} Numerical illustrations for the time-dependent Gross--Pitaevskii equation in the physically most relevant case of three space dimensions and for its parabolic counterpart related to ground state and excited state computations confirm the benefits of the proposed fourth-order modified operator splitting method in comparison with standard splitting methods. The presented results are novel and of particular interest from both, a theoretical perspective to inspire future investigations of modified operator splitting methods for other classes of nonlinear evolution equations and a practical perspective to advance the reliable and efficient simulation of Gross--Pitaevskii systems in real and imaginary time., Comment: 30 pages, 6 figures

As robotic systems increasingly encounter complex and unconstrained real-world scenarios, there is a demand to recognize diverse objects. The state-of-the-art 6D object pose estimation methods rely on object-specific training and therefore do not generalize to unseen objects. Recent novel object pose estimation methods are solving this issue using task-specific fine-tuned CNNs for deep template matching. This adaptation for pose estimation still requires expensive data rendering and training procedures. MegaPose for example is trained on a dataset consisting of two million images showing 20,000 different objects to reach such generalization capabilities. To overcome this shortcoming we introduce ZS6D, for zero-shot novel object 6D pose estimation. Visual descriptors, extracted using pre-trained Vision Transformers (ViT), are used for matching rendered templates against query images of objects and for establishing local correspondences. These local correspondences enable deriving geometric correspondences and are used for estimating the object's 6D pose with RANSAC-based PnP. This approach showcases that the image descriptors extracted by pre-trained ViTs are well-suited to achieve a notable improvement over two state-of-the-art novel object 6D pose estimation methods, without the need for task-specific fine-tuning. Experiments are performed on LMO, YCBV, and TLESS. In comparison to one of the two methods we improve the Average Recall on all three datasets and compared to the second method we improve on two datasets.

Background: We aimed at improving image quality (IQ) of sparse-view computed tomography (CT) images using a U-Net for lung metastasis detection and determining the best tradeoff between number of views, IQ, and diagnostic confidence. Methods: CT images from 41 subjects aged 62.8 $\pm$ 10.6 years (mean $\pm$ standard deviation), 23 men, 34 with lung metastasis, 7 healthy, were retrospectively selected (2016-2018) and forward projected onto 2,048-view sinograms. Six corresponding sparse-view CT data subsets at varying levels of undersampling were reconstructed from sinograms using filtered backprojection with 16, 32, 64, 128, 256, and 512 views. A dual-frame U-Net was trained and evaluated for each subsampling level on 8,658 images from 22 diseased subjects. A representative image per scan was selected from 19 subjects (12 diseased, 7 healthy) for a single-blinded multireader study. These slices, for all levels of subsampling, with and without U-Net postprocessing, were presented to three readers. IQ and diagnostic confidence were ranked using predefined scales. Subjective nodule segmentation was evaluated using sensitivity and Dice similarity coefficient (DSC); clustered Wilcoxon signed-rank test was used. Results: The 64-projection sparse-view images resulted in 0.89 sensitivity and 0.81 DSC, while their counterparts, postprocessed with the U-Net, had improved metrics (0.94 sensitivity and 0.85 DSC) (p = 0.400). Fewer views led to insufficient IQ for diagnosis. For increased views, no substantial discrepancies were noted between sparse-view and postprocessed images. Conclusions: Projection views can be reduced from 2,048 to 64 while maintaining IQ and the confidence of the radiologists on a satisfactory level.

Object pose estimation is a core perception task that enables, for example, object grasping and scene understanding. The widely available, inexpensive and high-resolution RGB sensors and CNNs that allow for fast inference based on this modality make monocular approaches especially well suited for robotics applications. We observe that previous surveys on object pose estimation establish the state of the art for varying modalities, single- and multi-view settings, and datasets and metrics that consider a multitude of applications. We argue, however, that those works' broad scope hinders the identification of open challenges that are specific to monocular approaches and the derivation of promising future challenges for their application in robotics. By providing a unified view on recent publications from both robotics and computer vision, we find that occlusion handling, novel pose representations, and formalizing and improving category-level pose estimation are still fundamental challenges that are highly relevant for robotics. Moreover, to further improve robotic performance, large object sets, novel objects, refractive materials, and uncertainty estimates are central, largely unsolved open challenges. In order to address them, ontological reasoning, deformability handling, scene-level reasoning, realistic datasets, and the ecological footprint of algorithms need to be improved., Comment: Accepted for publication in Transactions on Robotics: https://ieeexplore.ieee.org/document/10609560 arXiv admin note: substantial text overlap with arXiv:2302.11827

Object pose estimation is important for object manipulation and scene understanding. In order to improve the general applicability of pose estimators, recent research focuses on providing estimates for novel objects, that is objects unseen during training. Such works use deep template matching strategies to retrieve the closest template connected to a query image. This template retrieval implicitly provides object class and pose. Despite the recent success and improvements of Vision Transformers over CNNs for many vision tasks, the state of the art uses CNN-based approaches for novel object pose estimation. This work evaluates and demonstrates the differences between self-supervised CNNs and Vision Transformers for deep template matching. In detail, both types of approaches are trained using contrastive learning to match training images against rendered templates of isolated objects. At test time, such templates are matched against query images of known and novel objects under challenging settings, such as clutter, occlusion and object symmetries, using masked cosine similarity. The presented results not only demonstrate that Vision Transformers improve in matching accuracy over CNNs, but also that for some cases pre-trained Vision Transformers do not need fine-tuning to do so. Furthermore, we highlight the differences in optimization and network architecture when comparing these two types of network for deep template matching.

This is a preprint. The latest version has been published here: https://pubs.rsna.org/doi/10.1148/ryai.230275 Purpose: Sparse-view computed tomography (CT) is an effective way to reduce dose by lowering the total number of views acquired, albeit at the expense of image quality, which, in turn, can impact the ability to detect diseases. We explore deep learning-based artifact reduction in sparse-view cranial CT scans and its impact on automated hemorrhage detection. Methods: We trained a U-Net for artefact reduction on simulated sparse-view cranial CT scans from 3000 patients obtained from a public dataset and reconstructed with varying levels of sub-sampling. Additionally, we trained a convolutional neural network on fully sampled CT data from 17,545 patients for automated hemorrhage detection. We evaluated the classification performance using the area under the receiver operator characteristic curves (AUC-ROCs) with corresponding 95% confidence intervals (CIs) and the DeLong test, along with confusion matrices. The performance of the U-Net was compared to an analytical approach based on total variation (TV). Results: The U-Net performed superior compared to unprocessed and TV-processed images with respect to image quality and automated hemorrhage diagnosis. With U-Net post-processing, the number of views can be reduced from 4096 (AUC-ROC: 0.974; 95% CI: 0.972-0.976) views to 512 views (0.973; 0.971-0.975) with minimal decrease in hemorrhage detection (P<.001) and to 256 views (0.967; 0.964-0.969) with a slight performance decrease (P<.001). Conclusion: The results suggest that U-Net based artifact reduction substantially enhances automated hemorrhage detection in sparse-view cranial CTs. Our findings highlight that appropriate post-processing is crucial for optimal image quality and diagnostic accuracy while minimizing radiation dose., Comment: 11 pages, 6 figures, 1 table

We aim to optimize the binary detection of Chronic Obstructive Pulmonary Disease (COPD) based on emphysema presence in the lung with convolutional neural networks (CNN) by exploring manually adjusted versus automated window-setting optimization (WSO) on computed tomography (CT) images. 7,194 CT images (3,597 with COPD; 3,597 healthy controls) from 78 subjects (43 with COPD; 35 healthy controls) were selected retrospectively (10.2018-12.2019) and preprocessed. For each image, intensity values were manually clipped to the emphysema window setting and a baseline 'full-range' window setting. Class-balanced train, validation, and test sets contained 3,392, 1,114, and 2,688 images. The network backbone was optimized by comparing various CNN architectures. Furthermore, automated WSO was implemented by adding a customized layer to the model. The image-level area under the Receiver Operating Characteristics curve (AUC) [lower, upper limit 95% confidence] was utilized to compare model variations. Repeated inference (n=7) on the test set showed that the DenseNet was the most efficient backbone and achieved a mean AUC of 0.80 [0.76, 0.85] without WSO. Comparably, with input images manually adjusted to the emphysema window, the DenseNet model predicted COPD with a mean AUC of 0.86 [0.82, 0.89]. By adding a customized WSO layer to the DenseNet, an optimal window in the proximity of the emphysema window setting was learned automatically, and a mean AUC of 0.82 [0.78, 0.86] was achieved. Detection of COPD with DenseNet models was improved by WSO of CT data to the emphysema window setting range.

Object pose estimation is a non-trivial task that enables robotic manipulation, bin picking, augmented reality, and scene understanding, to name a few use cases. Monocular object pose estimation gained considerable momentum with the rise of high-performing deep learning-based solutions and is particularly interesting for the community since sensors are inexpensive and inference is fast. Prior works establish the comprehensive state of the art for diverse pose estimation problems. Their broad scopes make it difficult to identify promising future directions. We narrow down the scope to the problem of single-shot monocular 6D object pose estimation, which is commonly used in robotics, and thus are able to identify such trends. By reviewing recent publications in robotics and computer vision, the state of the art is established at the union of both fields. Following that, we identify promising research directions in order to help researchers to formulate relevant research ideas and effectively advance the state of the art. Findings include that methods are sophisticated enough to overcome the domain shift and that occlusion handling is a fundamental challenge. We also highlight problems such as novel object pose estimation and challenging materials handling as central challenges to advance robotics., Comment: Revised version in the making

Transparent objects are common in day-to-day life and hence find many applications that require robot grasping. Many solutions toward object grasping exist for non-transparent objects. However, due to the unique visual properties of transparent objects, standard 3D sensors produce noisy or distorted measurements. Modern approaches tackle this problem by either refining the noisy depth measurements or using some intermediate representation of the depth. Towards this, we study deep learning 6D pose estimation from RGB images only for transparent object grasping. To train and test the suitability of RGB-based object pose estimation, we construct a dataset of RGB-only images with 6D pose annotations. The experiments demonstrate the effectiveness of RGB image space for grasping transparent objects.

When accreting X-ray pulsars (XRPs) undergo bright X-ray outbursts, their luminosity-dependent spectral and timing features can be analysed in detail. The XRP GRO J1750-27 recently underwent one of such episodes, during which it was observed with $NuSTAR$ and monitored with $NICER$. Such a data set is rarely available, as it samples the outburst over more than a month at a luminosity that is always exceeding ${\sim}5\times10^{37}\,$erg/s. This value is larger than the typical critical luminosity value, where a radiative shock is formed above the neutron star's surface. Our data analysis of the joint spectra returns a highly ($N_H\sim(5-8)\times10^{22}\,$cm$^{-2}$) absorbed spectrum showing a K$\alpha$ iron line, a soft blackbody component likely originating from the inner edge of the accretion disk, and confirms the discovery of one of the deepest cyclotron lines, at a centroid energy of ${\sim}44\,$keV corresponding to a magnetic field strength of $4.7\times10^{12}\,$G. This value is independently supported by the best-fit physical model for spectral formation in accreting XRPs which, in agreement with recent findings, favours a distance of $14$ kpc and also reflects a bulk-Comptonization dominated accretion flow. Contrary to theoretical expectations and observational evidence from other similar sources, the pulse profiles as observed by $NICER$ through the outburst raise, peak and decay remain remarkably steady. The $NICER$ spectrum, including the iron K$\alpha$ line best-fit parameters, also remain almost unchanged at all probed outburst stages, similar to the pulsed fraction behaviour. We argue that all these phenomena are linked and interpret them as resulting from a saturation effect of the accretion column's emission, which occurs in the high-luminosity regime., Comment: Accepted on A&A -- proof version

Due to the structure of the NuSTAR telescope, photons at large off-axis (> 1deg) can reach the detectors directly (stray light), without passing through the instrument optics. At these off-axis angles NuSTAR essentially turns into a collimated instrument and the spectrum can extend to energies above the Pt k-edge (79 keV) of the multi-layers, which limits the effective area bandpass of the optics. We present the first scientific spectral analysis beyond 79 keV using a Cygnus X-1 observation in StrayCats, the catalog of stray light observations. This serendipitous stray light observation occurred simultaneously with an INTEGRAL observation. When the spectra are modeled together in the 30-120 keV energy band, we find that the NuSTAR stray light flux is well calibrated and constrained to be consistent with the INTEGRAL flux at the 90% confidence level. Furthermore, we explain how to treat the background of the stray light spectral analysis, which is especially important at high energies., Comment: Accepted for publication in ApJ

State-of-the-art object pose estimation handles multiple instances in a test image by using multi-model formulations: detection as a first stage and then separately trained networks per object for 2D-3D geometric correspondence prediction as a second stage. Poses are subsequently estimated using the Perspective-n-Points algorithm at runtime. Unfortunately, multi-model formulations are slow and do not scale well with the number of object instances involved. Recent approaches show that direct 6D object pose estimation is feasible when derived from the aforementioned geometric correspondences. We present an approach that learns an intermediate geometric representation of multiple objects to directly regress 6D poses of all instances in a test image. The inherent end-to-end trainability overcomes the requirement of separately processing individual object instances. By calculating the mutual Intersection-over-Unions, pose hypotheses are clustered into distinct instances, which achieves negligible runtime overhead with respect to the number of object instances. Results on multiple challenging standard datasets show that the pose estimation performance is superior to single-model state-of-the-art approaches despite being more than ~35 times faster. We additionally provide an analysis showing real-time applicability (>24 fps) for images where more than 90 object instances are present. Further results show the advantage of supervising geometric-correspondence-based object pose estimation with the 6D pose.