@article{BartoliSengupta2025, author = {Bartoli, Adrien and Sengupta, Agniva}, title = {Camera Pose in SfT and NRSfM under Isometric and Weaker Deformation Models}, volume = {261}, journal = {Computer Vision and Image Understanding}, doi = {10.1016/j.cviu.2025.104488}, year = {2025}, abstract = {Camera pose is a very natural concept in 3D vision in the rigid setting. It is however much more difficult to work with in deformable settings. Consequently, numerous deformable reconstruction methods simply ignore camera pose. We analyse the concept of pose in deformable settings and prove that it is unconstrained with the existing formulations, properly justifying the existing pose-less methods reconstructing structure only. We explain this result intuitively by the impossibility to define an intrinsic coordinate frame to a general deforming object. The proposed analysis uses the isometric deformation model and extends to the weaker models including conformality and equiareality. We propose a novel prior to rescue camera pose estimation in deformable settings, which attributes the deforming object's dominant rigid-body motion to the camera. We show that adding this prior to any existing formulation fully constrains camera pose and leads to elegant two-step solution methods, involving deformable structure reconstruction using a base method in the first step, and absolute orientation or Procrustes analysis in the second step. We derive the proposed approach for the template-based and template-less settings, respectively implemented using Shape-from-Template (SfT) and Non-Rigid Structure-from-Motion (NRSfM) as base methods, and validate them experimentally, showing that the computed pose is qualitatively and quantitatively plausible.}, language = {en} } @misc{DoerffelMikulaSchielickeetal.2025, author = {D{\"o}rffel, Tom and Mikula, Natalia and Schielicke, Lisa and Kiszler, Theresa and Faranda, Davide and Debrulle, B{\´e}reng{\`e}re and Vercauteren, Nikki}, title = {Characterizing inertial and diabatic energy transfers in tropical cyclones: Data}, doi = {10.12752/10135}, year = {2025}, abstract = {The multiscale organization of tropical cyclones (TCs) is investigated by means of three-dimensional data produced by the atmospheric model CM1. We provide a sample dataset in NetCDF format covering the TC evolution from incipient to mature under the influence of externally imposed wind shear. This dataset serves as a testbed for applying energy-tranfer analyses based on the Duchon-Robert index as well as diabatic transfer based on an asymptotic theory on TCs.}, language = {en} } @inproceedings{SchneiderSekulicPlocketal.2025, author = {Schneider, Philipp-Immanuel and Sekulic, Ivan and Plock, Matthias and Hammerschmidt, Martin and Rodt, Sven and Reitzenstein, Stephan and Burger, Sven}, title = {Physics-informed Bayesian optimization of nanophotonic devices}, volume = {IPRSN}, booktitle = {Advanced Photonics Congress}, doi = {10.1364/IPRSN.2025.ITu1A.2}, pages = {ITu1A.2}, year = {2025}, language = {en} } @article{ReussMacdonaldBeckeretal.2025, author = {Reuss, Joana and Macdonald, Jan and Becker, Simon and Schultka, Konrad and Richter, Lorenz and K{\"o}rner, Marco}, title = {Meta-learning For Few-Shot Time Series Crop Type Classification: A Benchmark On The EuroCropsML Dataset}, arxiv = {http://arxiv.org/abs/2504.11022}, year = {2025}, abstract = {Spatial imbalances in crop type data pose significant challenges for accurate classification in remote sensing applications. Algorithms aiming at transferring knowledge from data-rich to data-scarce tasks have thus surged in popularity. However, despite their effectiveness in previous evaluations, their performance in challenging real-world applications is unclear and needs to be evaluated. This study benchmarks transfer learning and several meta-learning algorithms, including (First-Order) Model-Agnostic Meta-Learning ((FO)-MAML), Almost No Inner Loop (ANIL), and Task-Informed Meta-Learning (TIML), on the real-world EuroCropsML time series dataset, which combines farmer-reported crop data with Sentinel-2 satellite observations from Estonia, Latvia, and Portugal. Our findings indicate that MAML-based meta-learning algorithms achieve slightly higher accuracy compared to simpler transfer learning methods when applied to crop type classification tasks in Estonia after pre-training on data from Latvia. However, this improvement comes at the cost of increased computational demands and training time. Moreover, we find that the transfer of knowledge between geographically disparate regions, such as Estonia and Portugal, poses significant challenges to all investigated algorithms. These insights underscore the trade-offs between accuracy and computational resource requirements in selecting machine learning methods for real-world crop type classification tasks and highlight the difficulties of transferring knowledge between different regions of the Earth. To facilitate future research in this domain, we present the first comprehensive benchmark for evaluating transfer and meta-learning methods for crop type classification under real-world conditions. The corresponding code is publicly available at this https URL.}, language = {en} } @inproceedings{ChenRichterBerneretal.2025, author = {Chen, Junhua and Richter, Lorenz and Berner, Julius and Blessing, Denis and Neumann, Gerhard and Anandkumar, Anima}, title = {Sequential Controlled Langevin Diffusions}, booktitle = {13th International Conference on Learning Representations (ICLR 2025)}, arxiv = {http://arxiv.org/abs/2412.07081}, year = {2025}, abstract = {An effective approach for sampling from unnormalized densities is based on the idea of gradually transporting samples from an easy prior to the complicated target distribution. Two popular methods are (1) Sequential Monte Carlo (SMC), where the transport is performed through successive annealed densities via prescribed Markov chains and resampling steps, and (2) recently developed diffusion-based sampling methods, where a learned dynamical transport is used. Despite the common goal, both approaches have different, often complementary, advantages and drawbacks. The resampling steps in SMC allow focusing on promising regions of the space, often leading to robust performance. While the algorithm enjoys asymptotic guarantees, the lack of flexible, learnable transitions can lead to slow convergence. On the other hand, diffusion-based samplers are learned and can potentially better adapt themselves to the target at hand, yet often suffer from training instabilities. In this work, we present a principled framework for combining SMC with diffusion-based samplers by viewing both methods in continuous time and considering measures on path space. This culminates in the new Sequential Controlled Langevin Diffusion (SCLD) sampling method, which is able to utilize the benefits of both methods and reaches improved performance on multiple benchmark problems, in many cases using only 10\% of the training budget of previous diffusion-based samplers.}, language = {en} } @article{BernerRichterSenderaetal.2025, author = {Berner, Julius and Richter, Lorenz and Sendera, Marcin and Rector-Brooks, Jarrid and Malkin, Nikolay}, title = {From discrete-time policies to continuous-time diffusion samplers: Asymptotic equivalences and faster training}, arxiv = {http://arxiv.org/abs/2501.06148}, year = {2025}, abstract = {We study the problem of training neural stochastic differential equations, or diffusion models, to sample from a Boltzmann distribution without access to target samples. Existing methods for training such models enforce time-reversal of the generative and noising processes, using either differentiable simulation or off-policy reinforcement learning (RL). We prove equivalences between families of objectives in the limit of infinitesimal discretization steps, linking entropic RL methods (GFlowNets) with continuous-time objects (partial differential equations and path space measures). We further show that an appropriate choice of coarse time discretization during training allows greatly improved sample efficiency and the use of time-local objectives, achieving competitive performance on standard sampling benchmarks with reduced computational cost.}, language = {en} } @inproceedings{BlessingBernerRichteretal.2025, author = {Blessing, Denis and Berner, Julius and Richter, Lorenz and Neumann, Gerhard}, title = {Underdamped Diffusion Bridges with Applications to Sampling}, booktitle = {13th International Conference on Learning Representations (ICLR 2025)}, arxiv = {http://arxiv.org/abs/2503.01006}, year = {2025}, abstract = {We provide a general framework for learning diffusion bridges that transport prior to target distributions. It includes existing diffusion models for generative modeling, but also underdamped versions with degenerate diffusion matrices, where the noise only acts in certain dimensions. Extending previous findings, our framework allows to rigorously show that score matching in the underdamped case is indeed equivalent to maximizing a lower bound on the likelihood. Motivated by superior convergence properties and compatibility with sophisticated numerical integration schemes of underdamped stochastic processes, we propose \emph{underdamped diffusion bridges}, where a general density evolution is learned rather than prescribed by a fixed noising process. We apply our method to the challenging task of sampling from unnormalized densities without access to samples from the target distribution. Across a diverse range of sampling problems, our approach demonstrates state-of-the-art performance, notably outperforming alternative methods, while requiring significantly fewer discretization steps and no hyperparameter tuning.}, language = {en} } @article{BlessingBernerRichteretal.2025, author = {Blessing, Denis and Berner, Julius and Richter, Lorenz and Domingo-Enrich, Carles and Du, Yuanqi and Vahdat, Arash and Neumann, Gerhard}, title = {Trust Region Constrained Measure Transport in Path Space for Stochastic Optimal Control and Inference}, arxiv = {http://arxiv.org/abs/2508.12511}, year = {2025}, abstract = {Solving stochastic optimal control problems with quadratic control costs can be viewed as approximating a target path space measure, e.g. via gradient-based optimization. In practice, however, this optimization is challenging in particular if the target measure differs substantially from the prior. In this work, we therefore approach the problem by iteratively solving constrained problems incorporating trust regions that aim for approaching the target measure gradually in a systematic way. It turns out that this trust region based strategy can be understood as a geometric annealing from the prior to the target measure, where, however, the incorporated trust regions lead to a principled and educated way of choosing the time steps in the annealing path. We demonstrate in multiple optimal control applications that our novel method can improve performance significantly, including tasks in diffusion-based sampling, transition path sampling, and fine-tuning of diffusion models.}, language = {en} } @article{ReussMacdonaldBeckeretal.2025, author = {Reuss, Joana and Macdonald, Jan and Becker, Simon and Richter, Lorenz and K{\"o}rner, Marco}, title = {The EuroCropsML time series benchmark dataset for few-shot crop type classification in Europe}, volume = {12}, journal = {Scientific Data}, doi = {10.1038/s41597-025-04952-7}, year = {2025}, abstract = {We introduce EuroCropsML, an analysis-ready remote sensing dataset based on the open-source EuroCrops collection, for machine learning (ML) benchmarking of time series crop type classification in Europe. It is the first time-resolved remote sensing dataset designed to benchmark transnational few-shot crop type classification algorithms that supports advancements in algorithmic development and research comparability. It comprises 706683 multi-class labeled data points across 176 crop classes. Each data point features a time series of per-parcel median pixel values extracted from Sentinel-2 L1C data and precise geospatial coordinates. EuroCropsML is publicly available on Zenodo.}, language = {en} } @article{EigenLadenburgerBrenceetal.2025, author = {Eigen, Lennart and Ladenburger, Pius and Brence, Blaž and Shubitidze, Ani and Baum, Daniel and Hildebrandt, Thomas and Brecht, Michael}, title = {Elephant trunk tip musculature reflects species differences in grasping behavior}, volume = {8}, journal = {Communications Biology}, doi = {10.1038/s42003-025-08998-6}, year = {2025}, abstract = {Elephants use their trunks, muscular hydrostats, to perform a plethora of tasks. Trunk tip morphology as well as grasping behavior differ between elephant species. While African savanna elephants (Loxodonta africana) use their dorsal and ventral finger for pinching movements, Asian elephants (Elephas maximus) prefer to wrap around objects with their one dorsal finger and ventral bulb trunk tip lip. Moreover, E. maximus can flip their ventral bulb backwards to clamp objects behind the trunk tip. Whether trunk tip musculature differs between elephant species and muscle architecture is reflected by preferred grasping behavior is, however, not clear. In this study, we performed dense muscle fascicle reconstruction of three L. africana and three E. maximus hemi-trunk tips using a combination of manual and automated segmentation of high-resolution microfocus tomography (microCT) scans. We distinguish three types of muscle fascicles: longitudinal (bending and shortening), radial (elongating) and transversal muscle fascicles (elongating). We found that trunk tips of L. africana consist to one third of longitudinal and two thirds radial/transversal muscle fascicles, likely aiding in their grasping behavior, while E. maximus trunk tips consist to two thirds of longitudinal and one third radial/transversal muscle fascicles, which is advantageous for their wrapping and backward clamping behavior.}, language = {en} }