arXiv subjects

Johannes Stegmaier

Publications and source records attributed to Johannes Stegmaier.

At least 19 recordsLinked to original sources

arXiv2026

Training-Free Stimulus Encoding for Retinal Implants via Sparse Projected Gradient Descent

Retinal implants aim to restore functional vision despite photoreceptor degeneration, yet are fundamentally constrained by low resolution electrode arrays and patient-specific perceptual distortions. Most deployed encoders rely on task-agnostic downsampling and linear brightness-to-amplitude mappings, which are suboptimal under realistic perceptual models. While global inverse problems have been formulated as neural networks, such approaches can be fast at inference, and can achieve high reconstruction fidelity, but require training and have limited generalizability to arbitrary inputs. We cast stimulus encoding as a constrained sparse least-squares problem under a linearized perceptual forward model. Our key observation is that the resulting perception matrix can be highly sparse, depending on patient and implant configuration. Building on this, we apply an efficient projected residual norm steepest descent solver that exploits sparsity and supports stimulus bounds via projection. In silico experiments across four simulated patients and implant resolutions from $15\times15$ to $100\times100$ electrodes demonstrate improved reconstruction fidelity, with up to $+0.265$ SSIM increase, $+12.4\,\mathrm{dB}$ PSNR, and $81.4\%$ MAE reduction on Fashion-MNIST compared to Lanczos downsampling.

eess.IV↗

arXiv2026

SelfMOTR: Revisiting MOTR with Self-Generating Detection Priors

End-to-end transformer architectures have driven significant progress in multi-object tracking by unifying detection and association into a single, heuristic-free framework. Despite these benefits, poor detection performance and the inherent conflict between detection and association in a joint architecture remain critical concerns. Recent approaches aim to mitigate these issues by employing advanced denoising or label assignment strategies, or by incorporating detection priors from external object detectors. In this paper, we propose SelfMOTR, a simple yet highly effective detector-free alternative that decouples proposal discovery from association using self-generated internal detection priors. Through extensive analysis and ablation studies, we show that end-to-end transformer trackers with joint detection-association decoding retain substantial hidden detection capacity, and we provide a practical detector-free mechanism for leveraging it. To shed light on these joint decoding dynamics, we draw inspiration from attention sink analyses in large language models, leveraging Track Attention Mass to show that standard generic queries exhibit unbalanced attention, frequently struggling to weigh track context against novel object discovery. SelfMOTR achieves highly competitive performance in complex, dynamic environments, yielding 69.2 HOTA on DanceTrack and leading with 71.1 HOTA on the Bird Flock Tracking (BFT) dataset. Project page: https://medem23.github.io/SM

cs.CV↗

arXiv2026

Semantic-Guided Multimodal Preprocessing for Vision Transformer-Based Clear Cell Renal Cell Carcinoma Grading

Clear cell renal cell carcinoma (CCRCC) grading is essential for treatment planning, yet existing approaches either analyze patch-level images directly or focus solely on nuclei-level classification, without linking to final tumor grading. We propose a semantic-guided multimodal preprocessing method that integrates nuclei classification maps from existing pre-trained models with RGB histopathology images for Vision Transformer (ViT)-based CCRCC grading. Our approach employs classification map channel concatenation and multiplicative modulation, with optimized overlays to leverage nuclei grading information, while preserving RGB textural features. Evaluation of multiple preprocessing strategies demonstrates that semantic-guided enhancement achieves 0.916 balanced accuracy, outperforming RGB-only baseline (0.707) and max-voting aggregation from prior studies (0.427). Sensitivity analysis reveals that this 21 percentage point improvement over baseline persists even under simulated perturbation at rates matching current state-of-the-art nuclei classification model error thresholds, suggesting both effective semantic utilization and practical robustness. These findings show that preprocessing-based multimodal fusion can leverage the diagnostic potential of existing imperfect nuclei classifiers, effectively bridging previously isolated fine-grained nuclear-level analysis with coarse-grained ViT-based patch classification. Per-class recall was consistent across grades (0.93, 0.91, 0.91), indicating that gains are not concentrated in the majority class. Because the sensitivity analysis perturbs ground-truth maps rather than predictions from an actual nuclei model, this result characterizes robustness under simulated error rather than deployment with a real upstream model, which remains for future work.

cs.CV↗

arXiv2026

PET-Adapter: Test-Time Domain Adaptation for Full and Limited-Angle PET Image Reconstruction

Positron Emission Tomography (PET) image reconstruction is inherently challenged by Poisson noise and physical degradation factors, which are further exacerbated in limited-angle acquisitions. While deep learning methods demonstrate promising performance, their generalization to unseen clinical data distributions remains limited without extensive retraining. We propose PET-Adapter, a test-time domain adaptation framework for generative PET reconstruction models pretrained solely on phantom data. Our method enables adaptation to clinical datasets with varying anatomies, tracers, and scanner configurations without requiring paired ground truth. PET-Adapter introduces layer-wise low-rank anatomical conditioning during adaptation and Ordered Subset Expectation Maximization-based warm-starting that initializes the generation from physics-informed reconstructions, reducing diffusion steps from 50 to 2 without compromising quality. Experiments across multiple clinical datasets demonstrate superior 3D reconstruction performance in both full-angle and limited-angle settings, highlighting the clinical feasibility and computational efficiency of the proposed approach.

cs.CV↗

arXiv2026

Learnable Sparsity for Vision Generative Models

Diffusion models have achieved impressive advancements in various vision tasks. However, these gains often rely on increasing model size, which escalates computational complexity and memory demands, complicating deployment, raising inference costs, and causing environmental impact. While some studies have explored pruning techniques to improve the memory efficiency of diffusion models, most existing methods require extensive retraining to retain the model performance. Retraining a modern large diffusion model is extremely costly and resource-intensive, which limits the practicality of these methods. In this work, we achieve low-cost diffusion pruning without retraining by proposing a model-agnostic structural pruning framework for diffusion models that learns a differentiable mask to sparsify the model. To ensure effective pruning that preserves the quality of the final denoised latent, we design a novel end-to-end pruning objective that spans the entire diffusion process. As end-to-end pruning is memory-intensive, we further propose time step gradient checkpointing, a technique that significantly reduces memory usage during optimization, enabling end-to-end pruning within a limited memory budget. Results on state-of-the-art U-Net diffusion models SDXL and diffusion transformers (FLUX) demonstrate that our method can effectively prune up to 20% parameters with minimal perceptible performance degradation, and notably, without the need for model retraining. We also showcase that our method can still prune on top of time step distilled diffusion models.

cs.CV↗

arXiv2026

A Pragmatic Note on Evaluating Generative Models with Fréchet Inception Distance for Retinal Image Synthesis

Fréchet Inception Distance (FID), computed with an ImageNet pretrained Inception-v3 network, is widely used as a state-of-the-art evaluation metric for generative models. It assumes that feature vectors from Inception-v3 follow a multivariate Gaussian distribution and calculates the 2-Wasserstein distance based on their means and covariances. While FID effectively measures how closely synthetic data match real data in many image synthesis tasks, the primary goal in biomedical generative models is often to enrich training datasets ideally with corresponding annotations. For this purpose, the gold standard for evaluating generative models is to incorporate synthetic data into downstream task training, such as classification and segmentation, to pragmatically assess its performance. In this paper, we examine cases from retinal imaging modalities, including color fundus photography and optical coherence tomography, where FID and its related metrics misalign with task-specific evaluation goals in classification and segmentation. We highlight the limitations of using various metrics, represented by FID and its variants, as evaluation criteria for these applications and address their potential caveats in broader biomedical imaging modalities and downstream tasks.

cs.CV↗

arXiv2026

Visual Fixation-Based Retinal Prosthetic Simulation

This study proposes a retinal prosthetic simulation framework driven by visual fixations, inspired by the saccade mechanism, and assesses performance improvements through end-to-end optimization in a classification task. Salient patches are predicted from input images using the self-attention map of a vision transformer to mimic visual fixations. These patches are then encoded by a trainable U-Net and simulated using the pulse2percept framework to predict visual percepts. By incorporating a learnable encoder, we aim to optimize the visual information transmitted to the retinal implant, addressing both the limited resolution of the electrode array and the distortion between the input stimuli and resulting phosphenes. The predicted percepts are evaluated using the self-supervised DINOv2 foundation model, with an optional learnable linear layer for classification accuracy. On a subset of the ImageNet validation set, the fixation-based framework achieves a classification accuracy of 87.72%, using computational parameters based on a real subject's physiological data, significantly outperforming the downsampling-based accuracy of 40.59% and approaching the healthy upper bound of 92.76%. Our approach shows promising potential for producing more semantically understandable percepts with the limited resolution available in retinal prosthetics.

cs.CV↗

arXiv2026

CellStyle: Improved Zero-Shot Cell Segmentation via Style Transfer

Cell microscopy data are abundant; however, corresponding segmentation annotations remain scarce. Moreover, variations in cell types, imaging devices, and staining techniques introduce significant domain gaps between datasets. As a result, even large, pretrained segmentation models trained on diverse datasets (source datasets) struggle to generalize to unseen datasets (target datasets). To overcome this generalization problem, we propose CellStyle, which improves the segmentation quality of such models without requiring labels for the target dataset, thereby enabling zero-shot adaptation. CellStyle transfers the attributes of an unannotated target dataset, such as texture, color, and noise, to the annotated source dataset. This transfer is performed while preserving the cell shapes of the source images, ensuring that the existing source annotations can still be used while maintaining the visual characteristics of the target dataset. The styled synthetic images with the existing annotations enable the finetuning of a generalist segmentation model for application to the unannotated target data. We demonstrate that CellStyle significantly improves zero-shot cell segmentation performance across diverse datasets by finetuning multiple segmentation models on the style-transferred data. The code will be made publicly available.

cs.LG↗

arXiv2025

Unconsciously Forget: Mitigating Memorization; Without Knowing What is being Memorized

Recent advances in generative models have demonstrated an exceptional ability to produce highly realistic images. However, previous studies show that generated images often resemble the training data, and this problem becomes more severe as the model size increases. Memorizing training data can lead to legal challenges, including copyright infringement, violations of portrait rights, and trademark violations. Existing approaches to mitigating memorization mainly focus on manipulating the denoising sampling process to steer image embeddings away from the memorized embedding space or employ unlearning methods that require training on datasets containing specific sets of memorized concepts. However, existing methods often incur substantial computational overhead during sampling, or focus narrowly on removing one or more groups of target concepts, imposing a significant limitation on their scalability. To understand and mitigate these problems, our work, UniForget, offers a new perspective on understanding the root cause of memorization. Our work demonstrates that specific parts of the model are responsible for copyrighted content generation. By applying model pruning, we can effectively suppress the probability of generating copyrighted content without targeting specific concepts while preserving the general generative capabilities of the model. Additionally, we show that our approach is both orthogonal and complementary to existing unlearning methods, thereby highlighting its potential to improve current unlearning and de-memorization techniques.

cs.CV↗

arXiv2025

Diffusion-based Sinogram Interpolation for Limited Angle PET

Accurate PET imaging increasingly requires methods that support unconstrained detector layouts from walk-through designs to long-axial rings where gaps and open sides lead to severely undersampled sinograms. Instead of constraining the hardware to form complete cylinders, we propose treating the missing lines-of-responses as a learnable prior. Data-driven approaches, particularly generative models, offer a promising pathway to recover this missing information. In this work, we explore the use of conditional diffusion models to interpolate sparsely sampled sinograms, paving the way for novel, cost-efficient, and patient-friendly PET geometries in real clinical settings.

cs.LG↗

arXiv2025

Segment Anything for Cell Tracking

Tracking cells and detecting mitotic events in time-lapse microscopy image sequences is a crucial task in biomedical research. However, it remains highly challenging due to dividing objects, low signal-tonoise ratios, indistinct boundaries, dense clusters, and the visually similar appearance of individual cells. Existing deep learning-based methods rely on manually labeled datasets for training, which is both costly and time-consuming. Moreover, their generalizability to unseen datasets remains limited due to the vast diversity of microscopy data. To overcome these limitations, we propose a zero-shot cell tracking framework by integrating Segment Anything 2 (SAM2), a large foundation model designed for general image and video segmentation, into the tracking pipeline. As a fully-unsupervised approach, our method does not depend on or inherit biases from any specific training dataset, allowing it to generalize across diverse microscopy datasets without finetuning. Our approach achieves competitive accuracy in both 2D and large-scale 3D time-lapse microscopy videos while eliminating the need for dataset-specific adaptation.

cs.CV↗

arXiv2025

SIS-Challenge: Event-based Spatio-temporal Instance Segmentation Challenge at the CVPR 2025 Event-based Vision Workshop

We present an overview of the Spatio-temporal Instance Segmentation (SIS) challenge held in conjunction with the CVPR 2025 Event-based Vision Workshop. The task is to predict accurate pixel-level segmentation masks of defined object classes from spatio-temporally aligned event camera and grayscale camera data. We provide an overview of the task, dataset, challenge details and results. Furthermore, we describe the methods used by the top-5 ranking teams in the challenge. More resources and code of the participants' methods are available here: https://github.com/tub-rip/MouseSIS/blob/main/docs/challenge_results.md

cs.CV↗

arXiv2025

Minimalist Concept Erasure in Generative Models

Recent advances in generative models have demonstrated remarkable capabilities in producing high-quality images, but their reliance on large-scale unlabeled data has raised significant safety and copyright concerns. Efforts to address these issues by erasing unwanted concepts have shown promise. However, many existing erasure methods involve excessive modifications that compromise the overall utility of the model. In this work, we address these issues by formulating a novel minimalist concept erasure objective based \emph{only} on the distributional distance of final generation outputs. Building on our formulation, we derive a tractable loss for differentiable optimization that leverages backpropagation through all generation steps in an end-to-end manner. We also conduct extensive analysis to show theoretical connections with other models and methods. To improve the robustness of the erasure, we incorporate neuron masking as an alternative to model fine-tuning. Empirical evaluations on state-of-the-art flow-matching models demonstrate that our method robustly erases concepts without degrading overall model performance, paving the way for safer and more responsible generative models.

cs.CV↗

arXiv2025

Towards Robust and Generalizable Gerchberg Saxton based Physics Inspired Neural Networks for Computer Generated Holography: A Sensitivity Analysis Framework

Computer-generated holography (CGH) enables applications in holographic augmented reality (AR), 3D displays, systems neuroscience, and optical trapping. The fundamental challenge in CGH is solving the inverse problem of phase retrieval from intensity measurements. Physics-inspired neural networks (PINNs), especially Gerchberg-Saxton-based PINNs (GS-PINNs), have advanced phase retrieval capabilities. However, their performance strongly depends on forward models (FMs) and their hyperparameters (FMHs), limiting generalization, complicating benchmarking, and hindering hardware optimization. We present a systematic sensitivity analysis framework based on Saltelli's extension of Sobol's method to quantify FMH impacts on GS-PINN performance. Our analysis demonstrates that SLM pixel-resolution is the primary factor affecting neural network sensitivity, followed by pixel-pitch, propagation distance, and wavelength. Free space propagation forward models demonstrate superior neural network performance compared to Fourier holography, providing enhanced parameterization and generalization. We introduce a composite evaluation metric combining performance consistency, generalization capability, and hyperparameter perturbation resilience, establishing a unified benchmarking standard across CGH configurations. Our research connects physics-inspired deep learning theory with practical CGH implementations through concrete guidelines for forward model selection, neural network architecture, and performance evaluation. Our contributions advance the development of robust, interpretable, and generalizable neural networks for diverse holographic applications, supporting evidence-based decisions in CGH research and implementation.

cs.CV↗

arXiv2025

Comparative Analysis of Unsupervised and Supervised Autoencoders for Nuclei Classification in Clear Cell Renal Cell Carcinoma Images

This study explores the application of supervised and unsupervised autoencoders (AEs) to automate nuclei classification in clear cell renal cell carcinoma (ccRCC) images, a diagnostic task traditionally reliant on subjective visual grading by pathologists. We evaluate various AE architectures, including standard AEs, contractive AEs (CAEs), and discriminative AEs (DAEs), as well as a classifier-based discriminative AE (CDAE), optimized using the hyperparameter tuning tool Optuna. Bhattacharyya distance is selected from several metrics to assess class separability in the latent space, revealing challenges in distinguishing adjacent grades using unsupervised models. CDAE, integrating a supervised classifier branch, demonstrated superior performance in both latent space separation and classification accuracy. Given that CDAE-CNN achieved notable improvements in classification metrics, affirming the value of supervised learning for class-specific feature extraction, F1 score was incorporated into the tuning process to optimize classification performance. Results show significant improvements in identifying aggressive ccRCC grades by leveraging the classification capability of AE through latent clustering followed by fine-grained classification. Our model outperforms the current state of the art, CHR-Network, across all evaluated metrics. These findings suggest that integrating a classifier branch in AEs, combined with neural architecture search and contrastive learning, enhances grading automation in ccRCC pathology, particularly in detecting aggressive tumor grades, and may improve diagnostic accuracy.

eess.IV↗

arXiv2025

Eye on the Target: Eye Tracking Meets Rodent Tracking

Analyzing animal behavior from video recordings is crucial for scientific research, yet manual annotation remains labor-intensive and prone to subjectivity. Efficient segmentation methods are needed to automate this process while maintaining high accuracy. In this work, we propose a novel pipeline that utilizes eye-tracking data from Aria glasses to generate prompt points, which are then used to produce segmentation masks via a fast zero-shot segmentation model. Additionally, we apply post-processing to refine the prompts, leading to improved segmentation quality. Through our approach, we demonstrate that combining eye-tracking-based annotation with smart prompt refinement can enhance segmentation accuracy, achieving an improvement of 70.6% from 38.8 to 66.2 in the Jaccard Index for segmentation results in the rats dataset.

cs.CV↗

arXiv2025

Unsupervised Learning for Feature Extraction and Temporal Alignment of 3D+t Point Clouds of Zebrafish Embryos

Zebrafish are widely used in biomedical research and developmental stages of their embryos often need to be synchronized for further analysis. We present an unsupervised approach to extract descriptive features from 3D+t point clouds of zebrafish embryos and subsequently use those features to temporally align corresponding developmental stages. An autoencoder architecture is proposed to learn a descriptive representation of the point clouds and we designed a deep regression network for their temporal alignment. We achieve a high alignment accuracy with an average mismatch of only 3.83 minutes over an experimental duration of 5.3 hours. As a fully-unsupervised approach, there is no manual labeling effort required and unlike manual analyses the method easily scales. Besides, the alignment without human annotation of the data also avoids any influence caused by subjective bias.

cs.CV↗

arXiv2025

Evaluating Cross-Subject and Cross-Device Consistency in Visual Fixation Prediction

Understanding cross-subject and cross-device consistency in visual fixation prediction is essential for advancing eye-tracking applications, including visual attention modeling and neuroprosthetics. This study evaluates fixation consistency using an embedded eye tracker integrated into regular-sized glasses, comparing its performance with high-end standalone eye-tracking systems. Nine participants viewed 300 images from the MIT1003 dataset in subjective experiments, allowing us to analyze cross-device and cross-subject variations in fixation patterns with various evaluation metrics. Our findings indicate that average visual fixations can be reliably transferred across devices for relatively simple stimuli. However, individual-to-average consistency remains weak, highlighting the challenges of predicting individual fixations across devices. These results provide an empirical foundation for leveraging predicted average visual fixation data to enhance neuroprosthetic applications.

cs.HC↗