Hannah Dröge

Hannah Dröge, Zorah Lähner, Yuval Bahat et al.

Permutation matrices play a key role in matching and assignment problems across the fields, especially in computer vision and robotics. However, memory for explicitly representing permutation matrices grows quadratically with the size of the problem, prohibiting large problem instances. In this work, we propose to tackle the curse of dimensionality of large permutation matrices by approximating them using low-rank matrix factorization, followed by a nonlinearity. To this end, we rely on the Kissing number theory to infer the minimal rank required for representing a permutation matrix of a given size, which is significantly smaller than the problem size. This leads to a drastic reduction in computation and memory costs, e.g., up to $3$ orders of magnitude less memory for a problem of size $n=20000$, represented using $8.4\times10^5$ elements in two small matrices instead of using a single huge matrix with $4\times 10^8$ elements. The proposed representation allows for accurate representations of large permutation matrices, which in turn enables handling large problems that would have been infeasible otherwise. We demonstrate the applicability and merits of the proposed approach through a series of experiments on a range of problems that involve predicting permutation matrices, from linear and quadratic assignment to shape matching problems.

Stefan Schulz, Fernando Edelstein, Hannah Dröge et al.

Real-time free-viewpoint rendering requires balancing multi-camera redundancy with the latency constraints of interactive applications. We address this challenge by combining lightweight geometry with learning and propose 3DTV, a feedforward network for real-time sparse-view interpolation. A Delaunay-based triplet selection ensures angular coverage for each target view. Building on this, we introduce a pose-aware depth module that estimates a coarse-to-fine depth pyramid, enabling efficient feature reprojection and occlusion-aware blending. Unlike methods that require scene-specific optimization, 3DTV runs feedforward without retraining, making it practical for AR/VR, telepresence, and interactive applications. Our experiments on challenging multi-view video datasets demonstrate that 3DTV consistently achieves a strong balance of quality and efficiency, outperforming recent real-time novel-view baselines. Crucially, 3DTV avoids explicit proxies, enabling robust rendering across diverse scenes. This makes it a practical solution for low-latency multi-view streaming and interactive rendering. Project Page: https://stefanmschulz.github.io/3DTV_webpage/

Julian Kaltheuner, Hannah Dröge, Markus Plack et al.

Temporally consistent surface reconstruction of dynamic 3D objects from unstructured point cloud data remains challenging, especially for very long sequences. Existing methods either optimize deformations incrementally, risking drift and requiring long runtimes, or rely on complex learned models that demand category-specific training. We present Neu-PiG, a fast deformation optimization method based on a novel preconditioned latent-grid encoding that distributes spatial features parameterized on the position and normal direction of a keyframe surface. Our method encodes entire deformations across all time steps at various spatial scales into a multi-resolution latent grid, parameterized by the position and normal direction of a reference surface from a single keyframe. This latent representation is then augmented for time modulation and decoded into per-frame 6-DoF deformations via a lightweight multilayer perceptron (MLP). To achieve high-fidelity, drift-free surface reconstructions in seconds, we employ Sobolev preconditioning during gradient-based training of the latent space, completely avoiding the need for any explicit correspondences or further priors. Experiments across diverse human and animal datasets demonstrate that Neu-PiG outperforms state-the-art approaches, offering both superior accuracy and scalability to long sequences while running at least 60x faster than existing training-free methods and achieving inference speeds on the same order as heavy pretrained models.

Hannah Dröge, Janelle Pfeifer, Saskia Rabich et al.

Capture stages are high-end sources of state-of-the-art recordings for downstream applications in movies, games, and other media. One crucial step in almost all pipelines is matting, i.e., separating captured performances from the background. While common matting algorithms deliver remarkable performance in other applications like teleconferencing and mobile entertainment, we found that they struggle significantly with the peculiarities of capture stage content. The goal of our work is to share insights into those challenges as a curated list of these characteristics along with a constructive discussion for proactive intervention and present a guideline to practitioners for an improved workflow to mitigate unresolved challenges. To this end, we also demonstrate an efficient pipeline to adapt state-of-the-art approaches to such custom setups without the need for extensive annotations, both offline and real-time. For an objective evaluation, we introduce a validation methodology using a state-of-the-art diffusion model to demonstrate the benefits of our approach.

Leif Van Holland, Domenic Zingsheim, Mana Takhsha et al.

High-quality 3D streaming from multiple cameras is crucial for immersive experiences in many AR/VR applications. The limited number of views - often due to real-time constraints - leads to missing information and incomplete surfaces in the rendered images. Existing approaches typically rely on simple heuristics for the hole filling, which can result in inconsistencies or visual artifacts. We propose to complete the missing textures using a novel, application-targeted inpainting method independent of the underlying representation as an image-based post-processing step after the novel view rendering. The method is designed as a standalone module compatible with any calibrated multi-camera system. For this we introduce a multi-view aware, transformer-based network architecture using spatio-temporal embeddings to ensure consistency across frames while preserving fine details. Additionally, our resolution-independent design allows adaptation to different camera setups, while an adaptive patch selection strategy balances inference speed and quality, allowing real-time performance. We evaluate our approach against state-of-the-art inpainting techniques under the same real-time constraints and demonstrate that our model achieves the best trade-off between quality and speed, outperforming competitors in both image and video-based metrics.

Elisabeth Jüttner, Leona Krath, Stefan Korfhage et al.

Volumetric video relighting is essential for bringing captured performances into virtual worlds, but current approaches struggle to deliver temporally stable, production-ready results. Diffusion-based intrinsic decomposition methods show promise for single frames, yet suffer from stochastic noise and instability when extended to sequences, while video diffusion models remain constrained by memory and scale. We propose a hybrid relighting framework that combines diffusion-derived material priors with temporal regularization and physically motivated rendering. Our method aggregates multiple stochastic estimates of per-frame material properties into temporally consistent shading components, using optical-flow-guided regularization. For indirect effects such as shadows and reflections, we extract a mesh proxy from Gaussian Opacity Fields and render it within a standard graphics pipeline. Experiments on real and synthetic captures show that this hybrid strategy achieves substantially more stable relighting across sequences than diffusion-only baselines, while scaling beyond the clip lengths feasible for video diffusion. These results indicate that hybrid approaches, which balance learned priors with physically grounded constraints, are a practical step toward production-ready volumetric video relighting.

Markus Plack, Hannah Dröge, Leif Van Holland et al.

We present a stereo-matching method for depth estimation from high-resolution images using visual hulls as priors, and a memory-efficient technique for the correlation computation. Our method uses object masks extracted from supplementary views of the scene to guide the disparity estimation, effectively reducing the search space for matches. This approach is specifically tailored to stereo rigs in volumetric capture systems, where an accurate depth plays a key role in the downstream reconstruction task. To enable training and regression at high resolutions targeted by recent systems, our approach extends a sparse correlation computation into a hybrid sparse-dense scheme suitable for application in leading recurrent network architectures. We evaluate the performance-efficiency trade-off of our method compared to state-of-the-art methods, and demonstrate the efficacy of the visual hull guidance. In addition, we propose a training scheme for a further reduction of memory requirements during optimization, facilitating training on high-resolution data.

Jonas Geiping, Hartmut Bauermeister, Hannah Dröge et al.

The idea of federated learning is to collaboratively train a neural network on a server. Each user receives the current weights of the network and in turns sends parameter updates (gradients) based on local data. This protocol has been designed not only to train neural networks data-efficiently, but also to provide privacy benefits for users, as their input data remains on device and only parameter gradients are shared. But how secure is sharing parameter gradients? Previous attacks have provided a false sense of security, by succeeding only in contrived settings - even for a single image. However, by exploiting a magnitude-invariant loss along with optimization strategies based on adversarial attacks, we show that is is actually possible to faithfully reconstruct images at high resolution from the knowledge of their parameter gradients, and demonstrate that such a break of privacy is possible even for trained deep networks. We analyze the effects of architecture as well as parameters on the difficulty of reconstructing an input image and prove that any input to a fully connected layer can be reconstructed analytically independent of the remaining architecture. Finally we discuss settings encountered in practice and show that even averaging gradients over several iterations or several images does not protect the user's privacy in federated learning applications in computer vision.