Jonathan Aellen

Dennis Madsen, Jonathan Aellen, Andreas Morel-Forster et al.

In this paper, we unify popular non-rigid registration methods for point sets and surfaces under our general framework, GiNGR. GiNGR builds upon Gaussian Process Morphable Models (GPMM) and hence separates modeling the deformation prior from model adaptation for registration. In addition, it provides explainable hyperparameters, multi-resolution registration, trivial inclusion of expert annotation, and the ability to use and combine analytical and statistical deformation priors. But more importantly, the reformulation allows for a direct comparison of registration methods. Instead of using a general solver in the optimization step, we show how Gaussian process regression (GPR) iteratively can warp a reference onto a target, leading to smooth deformations following the prior for any dense, sparse, or partial estimated correspondences in a principled way. We show how the popular CPD and ICP algorithms can be directly explained with GiNGR. Furthermore, we show how existing algorithms in the GiNGR framework can perform probabilistic registration to obtain a distribution of different registrations instead of a single best registration. This can be used to analyze the uncertainty e.g. when registering partial observations. GiNGR is publicly available and fully modular to allow for domain-specific prior construction.

Marcello Massimo Negri, Jonathan Aellen, Manuel Jahn et al.

Current density modeling approaches suffer from at least one of the following shortcomings: expensive training, slow inference, approximate likelihood, mode collapse or architectural constraints like bijective mappings. We propose a simple yet powerful framework that overcomes these limitations altogether. We define our model $q_θ(x)$ through a parametric distribution $q(x|w)$ with latent parameters $w$. Instead of directly optimizing the latent variables $w$, our idea is to marginalize them out by sampling $w$ from a learnable distribution $q_θ(w)$, hence the name Marginal Flow. In order to evaluate the learned density $q_θ(x)$ or to sample from it, we only need to draw samples from $q_θ(w)$, which makes both operations efficient. The proposed model allows for exact density evaluation and is orders of magnitude faster than competing models both at training and inference. Furthermore, Marginal Flow is a flexible framework: it does not impose any restrictions on the neural network architecture, it enables learning distributions on lower-dimensional manifolds (either known or to be learned), it can be trained efficiently with any objective (e.g. forward and reverse KL divergence), and it easily handles multi-modal targets. We evaluate Marginal Flow extensively on various tasks including synthetic datasets, simulation-based inference, distributions on positive definite matrices and manifold learning in latent spaces of images.

Jonathan Aellen, Florian Burkhardt, Thomas Vetter et al.

In medical imaging, point distribution models are often used to reconstruct and complete partial shapes using a statistical model of the full shape. A commonly overlooked, but crucial factor in this reconstruction process, is the pose of the training data relative to the partial target shape. A difference in pose alignment of the training and target shape leads to biased solutions, particularly when observing small parts of a shape. In this paper, we demonstrate the importance of pose alignment for partial shape reconstructions and propose an efficient method to adjust an existing model to a specific target. Our method preserves the computational efficiency of linear models while significantly improving reconstruction accuracy and predicted variance. It exactly recovers the intended aligned model for translations, and provides a good approximation for small rotations, all without access to the original training data. Hence, existing shape models in reconstruction pipelines can be adapted by a simple preprocessing step, making our approach widely applicable in plug-and-play scenarios.

Marcello Massimo Negri, Jonathan Aellen, Volker Roth

Normalizing Flows (NFs) are powerful and efficient models for density estimation. When modeling densities on manifolds, NFs can be generalized to injective flows but the Jacobian determinant becomes computationally prohibitive. Current approaches either consider bounds on the log-likelihood or rely on some approximations of the Jacobian determinant. In contrast, we propose injective flows for star-like manifolds and show that for such manifolds we can compute the Jacobian determinant exactly and efficiently, with the same cost as NFs. This aspect is particularly relevant for variational inference settings, where no samples are available and only some unnormalized target is known. Among many, we showcase the relevance of modeling densities on star-like manifolds in two settings. Firstly, we introduce a novel Objective Bayesian approach for penalized likelihood models by interpreting level-sets of the penalty as star-like manifolds. Secondly, we consider probabilistic mixing models and introduce a general method for variational inference by defining the posterior of mixture weights on the probability simplex.

F. Arend Torres, Marcello Massimo Negri, Marco Inversi et al.

We introduce Lagrangian Flow Networks (LFlows) for modeling fluid densities and velocities continuously in space and time. By construction, the proposed LFlows satisfy the continuity equation, a PDE describing mass conservation in its differentiable form. Our model is based on the insight that solutions to the continuity equation can be expressed as time-dependent density transformations via differentiable and invertible maps. This follows from classical theory of the existence and uniqueness of Lagrangian flows for smooth vector fields. Hence, we model fluid densities by transforming a base density with parameterized diffeomorphisms conditioned on time. The key benefit compared to methods relying on numerical ODE solvers or PINNs is that the analytic expression of the velocity is always consistent with changes in density. Furthermore, we require neither expensive numerical solvers, nor additional penalties to enforce the PDE. LFlows show higher predictive accuracy in density modeling tasks compared to competing models in 2D and 3D, while being computationally efficient. As a real-world application, we model bird migration based on sparse weather radar measurements.