Brian B. Moser

Sachin Kumar Singh, Ko Watanabe, Brian Moser et al.

The success of machine learning is deeply linked to the availability of high-quality training data, yet retrieving and manually labeling new data remains a time-consuming and error-prone process. Traditional annotation tools, such as Label Studio, often require post-processing, where users label data after it has been recorded. Post-processing is highly time-consuming and labor-intensive, especially with large datasets, and may lead to erroneous annotations due to the difficulty of subjects' memory tasks when labeling cognitive activities such as emotions or comprehension levels. In this work, we introduce HandyLabel, a real-time annotation tool that leverages hand gesture recognition to map hand signs for labeling. The application enables users to customize gesture mappings through a web-based interface, allowing for real-time annotations. To ensure the performance of HandyLabel, we evaluate several hand gesture recognition models on an open-source hand sign (HaGRID) dataset, with and without skeleton-based preprocessing. We discovered that ResNet50 with preprocessed skeleton-based images performs an F1-score of 0.923. To validate the usability of HandyLabel, a user study was conducted with 46 participants. The results suggest that 88.9% of participants preferred HandyLabel over traditional annotation tools.

Brian Moser, Federico Raue, Stanislav Frolov et al.

With the advent of Deep Learning (DL), Super-Resolution (SR) has also become a thriving research area. However, despite promising results, the field still faces challenges that require further research e.g., allowing flexible upsampling, more effective loss functions, and better evaluation metrics. We review the domain of SR in light of recent advances, and examine state-of-the-art models such as diffusion (DDPM) and transformer-based SR models. We present a critical discussion on contemporary strategies used in SR, and identify promising yet unexplored research directions. We complement previous surveys by incorporating the latest developments in the field such as uncertainty-driven losses, wavelet networks, neural architecture search, novel normalization methods, and the latests evaluation techniques. We also include several visualizations for the models and methods throughout each chapter in order to facilitate a global understanding of the trends in the field. This review is ultimately aimed at helping researchers to push the boundaries of DL applied to SR.

Brian Moser, Stanislav Frolov, Federico Raue et al.

This paper presents a novel Diffusion-Wavelet (DiWa) approach for Single-Image Super-Resolution (SISR). It leverages the strengths of Denoising Diffusion Probabilistic Models (DDPMs) and Discrete Wavelet Transformation (DWT). By enabling DDPMs to operate in the DWT domain, our DDPM models effectively hallucinate high-frequency information for super-resolved images on the wavelet spectrum, resulting in high-quality and detailed reconstructions in image space. Quantitatively, we outperform state-of-the-art diffusion-based SISR methods, namely SR3 and SRDiff, regarding PSNR, SSIM, and LPIPS on both face (8x scaling) and general (4x scaling) SR benchmarks. Meanwhile, using DWT enabled us to use fewer parameters than the compared models: 92M parameters instead of 550M compared to SR3 and 9.3M instead of 12M compared to SRDiff. Additionally, our method outperforms other state-of-the-art generative methods on classical general SR datasets while saving inference time. Finally, our work highlights its potential for various applications.

Brian Moser, Federico Raue, Jörn Hees et al.

Neural Architecture Search (NAS) defines the design of Neural Networks as a search problem. Unfortunately, NAS is computationally intensive because of various possibilities depending on the number of elements in the design and the possible connections between them. In this work, we extensively analyze the role of the dataset size based on several sampling approaches for reducing the dataset size (unsupervised and supervised cases) as an agnostic approach to reduce search time. We compared these techniques with four common NAS approaches in NAS-Bench-201 in roughly 1,400 experiments on CIFAR-100. One of our surprising findings is that in most cases we can reduce the amount of training data to 25\%, consequently reducing search time to 25\%, while at the same time maintaining the same accuracy as if training on the full dataset. Additionally, some designs derived from subsets out-perform designs derived from the full dataset by up to 22 p.p. accuracy.

Stanislav Frolov, Brian B. Moser, Andreas Dengel

Generating high-resolution images with generative models has recently been made widely accessible by leveraging diffusion models pre-trained on large-scale datasets. Various techniques, such as MultiDiffusion and SyncDiffusion, have further pushed image generation beyond training resolutions, i.e., from square images to panorama, by merging multiple overlapping diffusion paths or employing gradient descent to maintain perceptual coherence. However, these methods suffer from significant computational inefficiencies due to generating and averaging numerous predictions, which is required in practice to produce high-quality and seamless images. This work addresses this limitation and presents a novel approach that eliminates the need to generate and average numerous overlapping denoising predictions. Our method shifts non-overlapping denoising windows over time, ensuring that seams in one timestep are corrected in the next. This results in coherent, high-resolution images with fewer overall steps. We demonstrate the effectiveness of our approach through qualitative and quantitative evaluations, comparing it with MultiDiffusion, SyncDiffusion, and StitchDiffusion. Our method offers several key benefits, including improved computational efficiency and faster inference times while producing comparable or better image quality. Link to code https://github.com/stanifrolov/spotdiffusion

Brian B. Moser, Stanislav Frolov, Federico Raue et al.

Diffusion models in image Super-Resolution (SR) treat all image regions uniformly, which risks compromising the overall image quality by potentially introducing artifacts during denoising of less-complex regions. To address this, we propose ``You Only Diffuse Areas'' (YODA), a dynamic attention-guided diffusion process for image SR. YODA selectively focuses on spatial regions defined by attention maps derived from the low-resolution images and the current denoising time step. This time-dependent targeting enables a more efficient conversion to high-resolution outputs by focusing on areas that benefit the most from the iterative refinement process, i.e., detail-rich objects. We empirically validate YODA by extending leading diffusion-based methods SR3, DiffBIR, and SRDiff. Our experiments demonstrate new state-of-the-art performances in face and general SR tasks across PSNR, SSIM, and LPIPS metrics. As a side effect, we find that YODA reduces color shift issues and stabilizes training with small batches.

Brian B. Moser, Stanislav Frolov, Federico Raue et al.

This work introduces Differential Wavelet Amplifier (DWA), a drop-in module for wavelet-based image Super-Resolution (SR). DWA invigorates an approach recently receiving less attention, namely Discrete Wavelet Transformation (DWT). DWT enables an efficient image representation for SR and reduces the spatial area of its input by a factor of 4, the overall model size, and computation cost, framing it as an attractive approach for sustainable ML. Our proposed DWA model improves wavelet-based SR models by leveraging the difference between two convolutional filters to refine relevant feature extraction in the wavelet domain, emphasizing local contrasts and suppressing common noise in the input signals. We show its effectiveness by integrating it into existing SR models, e.g., DWSR and MWCNN, and demonstrate a clear improvement in classical SR tasks. Moreover, DWA enables a direct application of DWSR and MWCNN to input image space, reducing the DWT representation channel-wise since it omits traditional DWT.

Brian Moser, Federico Raue, Jörn Hees et al.

We present new Recurrent Neural Network (RNN) cells for image classification using a Neural Architecture Search (NAS) approach called DARTS. We are interested in the ReNet architecture, which is a RNN based approach presented as an alternative for convolutional and pooling steps. ReNet can be defined using any standard RNN cells, such as LSTM and GRU. One limitation is that standard RNN cells were designed for one dimensional sequential data and not for two dimensions like it is the case for image classification. We overcome this limitation by using DARTS to find new cell designs. We compare our results with ReNet that uses GRU and LSTM cells. Our found cells outperform the standard RNN cells on CIFAR-10 and SVHN. The improvements on SVHN indicate generalizability, as we derived the RNN cell designs from CIFAR-10 without performing a new cell search for SVHN.

Vijul Shah, Ko Watanabe, Brian B. Moser et al.

Measuring pupil diameter is vital for gaining insights into physiological and psychological states - traditionally captured by expensive, specialized equipment like Tobii eye-trackers and Pupillabs glasses. This paper presents a novel application that enables pupil diameter estimation using standard webcams, making the process accessible in everyday environments without specialized equipment. Our app estimates pupil diameters from videos and offers detailed analysis, including class activation maps, graphs of predicted left and right pupil diameters, and eye aspect ratios during blinks. This tool expands the accessibility of pupil diameter measurement, particularly in everyday settings, benefiting fields like human behavior research and healthcare. Additionally, we present a new open source dataset for pupil diameter estimation using webcam images containing cropped eye images and corresponding pupil diameter measurements.

Ahmed Anwar, Brian Moser, Dayananda Herurkar et al.

The emergence of federated learning (FL) presents a promising approach to leverage decentralized data while preserving privacy. Furthermore, the combination of FL and anomaly detection is particularly compelling because it allows for detecting rare and critical anomalies (usually also rare in locally gathered data) in sensitive data from multiple sources, such as cybersecurity and healthcare. However, benchmarking the performance of anomaly detection methods in FL environments remains an underexplored area. This paper introduces FedAD-Bench, a unified benchmark for evaluating unsupervised anomaly detection algorithms within the context of FL. We systematically analyze and compare the performance of recent deep learning anomaly detection models under federated settings, which were typically assessed solely in centralized settings. FedAD-Bench encompasses diverse datasets and metrics to provide a holistic evaluation. Through extensive experiments, we identify key challenges such as model aggregation inefficiencies and metric unreliability. We present insights into FL's regularization effects, revealing scenarios in which it outperforms centralized approaches due to its inherent ability to mitigate overfitting. Our work aims to establish a standardized benchmark to guide future research and development in federated anomaly detection, promoting reproducibility and fair comparison across studies.

Brian B. Moser, Federico Raue, Sebastian Palacio et al.

Dataset distillation seeks to condense datasets into smaller but highly representative synthetic samples. While diffusion models now lead all generative benchmarks, current distillation methods avoid them and rely instead on GANs or autoencoders, or, at best, sampling from a fixed diffusion prior. This trend arises because naive backpropagation through the long denoising chain leads to vanishing gradients, which prevents effective synthetic sample optimization. To address this limitation, we introduce Latent Dataset Distillation with Diffusion Models (LD3M), the first method to learn gradient-based distilled latents and class embeddings end-to-end through a pre-trained latent diffusion model. A linearly decaying skip connection, injected from the initial noisy state into every reverse step, preserves the gradient signal across dozens of timesteps without requiring diffusion weight fine-tuning. Across multiple ImageNet subsets at 128x128 and 256x256, LD3M improves downstream accuracy by up to 4.8 percentage points (1 IPC) and 4.2 points (10 IPC) over the prior state-of-the-art. The code for LD3M is provided at https://github.com/Brian-Moser/prune_and_distill.

Vijul Shah, Brian B. Moser, Ko Watanabe et al.

Capturing pupil diameter is essential for assessing psychological and physiological states such as stress levels and cognitive load. However, the low resolution of images in eye datasets often hampers precise measurement. This study evaluates the impact of various upscaling methods, ranging from bicubic interpolation to advanced super-resolution, on pupil diameter predictions. We compare several pre-trained methods, including CodeFormer, GFPGAN, Real-ESRGAN, HAT, and SRResNet. Our findings suggest that pupil diameter prediction models trained on upscaled datasets are highly sensitive to the selected upscaling method and scale. Our results demonstrate that upscaling methods consistently enhance the accuracy of pupil diameter prediction models, highlighting the importance of upscaling in pupilometry. Overall, our work provides valuable insights for selecting upscaling techniques, paving the way for more accurate assessments in psychological and physiological research.

Krzysztof Adamkiewicz, Brian Moser, Stanislav Frolov et al.

Recent text-to-image (T2I) diffusion models produce visually stunning images and demonstrate excellent prompt following. But do they perform well as synthetic vision data generators? In this work, we revisit the promise of synthetic data as a scalable substitute for real training sets and uncover a surprising performance regression. We generate large-scale synthetic datasets using state-of-the-art T2I models released between 2022 and 2025, train standard classifiers solely on this synthetic data, and evaluate them on real test data. Despite observable advances in visual fidelity and prompt adherence, classification accuracy on real test data consistently declines with newer T2I models as training data generators. Our analysis reveals a hidden trend: These models collapse to a narrow, aesthetic-centric distribution that undermines diversity and label-image alignment. Overall, our findings challenge a growing assumption in vision research, namely that progress in generative realism implies progress in data realism. We thus highlight an urgent need to rethink the capabilities of modern T2I models as reliable training data generators.

Brian B. Moser, Shalini Strode, Federico Raue et al.

Dataset distillation (DD) promises compact yet faithful synthetic data, but existing approaches often inherit the inductive bias of a single teacher model. As dataset size increases, this bias drives generation toward overly smooth, homogeneous samples, reducing intra-class diversity and limiting generalization. We present PRISM (PRIors from diverse Source Models), a framework that disentangles architectural priors during synthesis. PRISM decouples the logit-matching and regularization objectives, supervising them with different teacher architectures: a primary model for logits and a stochastic subset for batch-normalization (BN) alignment. On ImageNet-1K, PRISM consistently and reproducibly outperforms single-teacher methods (e.g., SRe2L) and recent multi-teacher variants (e.g., G-VBSM) at low- and mid-IPC regimes. The generated data also show significantly richer intra-class diversity, as reflected by a notable drop in cosine similarity between features. We further analyze teacher selection strategies (pre- vs. intra-distillation) and introduce a scalable cross-class batch formation scheme for fast parallel synthesis. Code will be released after the review period.

Tobias Christian Nauen, Stanislav Frolov, Brian Bernhard Moser et al.

The platonic representation hypothesis suggests that sufficiently large models converge to a shared representation geometry, even across modalities. Motivated by this, we ask: Can the semantic knowledge of a language model efficiently improve a vision model? As an answer, we introduce TextTeacher, a simple auxiliary objective that injects text embeddings as additional information into image classification training. TextTeacher uses readily available image captions, a pre-trained and frozen text encoder, and a lightweight projection to produce semantic anchors that efficiently guide representations during training while leaving the inference-time model unchanged. On ImageNet with standard ViT backbones, TextTeacher improves accuracy by up to +2.7 percentage points (p.p.) and yields consistent transfer gains (on average +1.0 p.p.) under the same recipe and compute. It outperforms vision knowledge distillation, yielding more accuracy at a constant compute budget or similar accuracy, but 33% faster. Our analysis indicates that TextTeacher acts as a feature-space preconditioner, shaping deeper layers in the first stages of training, and aiding generalization by supplying complementary semantic cues. TextTeacher adds negligible overhead, requires no costly multimodal training of the target model and preserves the simplicity and latency of pure vision models. Project page with code and captions: https://nauen-it.de/publications/text-teacher

Ryugo Morita, Stanislav Frolov, Brian Bernhard Moser et al.

Diffusion models have demonstrated high-quality performance in conditional text-to-image generation, particularly with structural cues such as edges, layouts, and depth. However, lighting conditions have received limited attention and remain difficult to control within the generative process. Existing methods handle lighting through a two-stage pipeline that relights images after generation, which is inefficient. Moreover, they rely on fine-tuning with large datasets and heavy computation, limiting their adaptability to new models and tasks. To address this, we propose a novel Training-Free Light-Guided Text-to-Image Diffusion Model via Initial Noise Manipulation (LGTM), which manipulates the initial latent noise of the diffusion process to guide image generation with text prompts and user-specified light directions. Through a channel-wise analysis of the latent space, we find that selectively manipulating latent channels enables fine-grained lighting control without fine-tuning or modifying the pre-trained model. Extensive experiments show that our method surpasses prompt-based baselines in lighting consistency, while preserving image quality and text alignment. This approach introduces new possibilities for dynamic, user-guided light control. Furthermore, it integrates seamlessly with models like ControlNet, demonstrating adaptability across diverse scenarios.

Ryugo Morita, Stanislav Frolov, Brian Bernhard Moser et al.

Layered image assets are widely used in real-world creative workflows, enabling non-destructive iteration and flexible re-composition. Recent advances in layered image generation and decomposition synthesize or recover layered representations, yet controllable editing of layered images remains challenging. Manual editing requires careful coordination across layers to maintain consistent illumination and contact, while AI-based pipelines collapse layers into a flattened image for editing, then decompose them again, introducing background-to-foreground leakage and unstable transparency. To address these limitations, we propose LimeCross, a training-free context-conditioned layered image editing framework that edits user-selected RGBA layers according to text while keeping the remaining layers unchanged. It leverages contextual cues from other layers using a bi-stream attention mechanism to preserve cross-layer consistency, while explicitly maintaining layer integrity to prevent the contamination of edited layers. To evaluate our approach, we introduce LayerEditBench, a benchmark of 1500 layered scenes with paired source/target prompts, along with evaluation protocols that assess both edit fidelity and alpha channel stability. Extensive experiments demonstrate that LimeCross improves layer purity and composite realism over strong editing baselines, establishing context-conditioned layered editing as a principled framework for controllable generative creation.

Tobias Christian Nauen, Brian Moser, Federico Raue et al.

Transformers, particularly Vision Transformers (ViTs), have achieved state-of-the-art performance in large-scale image classification. However, they often require large amounts of data and can exhibit biases that limit their robustness and generalizability. This paper introduces ForAug, a novel data augmentation scheme that addresses these challenges and explicitly includes inductive biases, which commonly are part of the neural network architecture, into the training data. ForAug is constructed by using pretrained foundation models to separate and recombine foreground objects with different backgrounds, enabling fine-grained control over image composition during training. It thus increases the data diversity and effective number of training samples. We demonstrate that training on ForNet, the application of ForAug to ImageNet, significantly improves the accuracy of ViTs and other architectures by up to 4.5 percentage points (p.p.) on ImageNet and 7.3 p.p. on downstream tasks. Importantly, ForAug enables novel ways of analyzing model behavior and quantifying biases. Namely, we introduce metrics for background robustness, foreground focus, center bias, and size bias and show that training on ForNet substantially reduces these biases compared to training on ImageNet. In summary, ForAug provides a valuable tool for analyzing and mitigating biases, enabling the development of more robust and reliable computer vision models. Our code and dataset are publicly available at https://github.com/tobna/ForAug.

Timon Winter, Stanislav Frolov, Brian Bernhard Moser et al.

Recent advancements in text-to-image (T2I) have improved synthesis results, but challenges remain in layout control and generating omnidirectional panoramic images. Dense T2I (DT2I) and spherical T2I (ST2I) models address these issues, but so far no unified approach exists. Trivial approaches, like prompting a DT2I model to generate panoramas can not generate proper spherical distortions and seamless transitions at the borders. Our work shows that spherical dense text-to-image (SDT2I) can be achieved by integrating training-free DT2I approaches into finetuned panorama models. Specifically, we propose MultiStitchDiffusion (MSTD) and MultiPanFusion (MPF) by integrating MultiDiffusion into StitchDiffusion and PanFusion, respectively. Since no benchmark for SDT2I exists, we further construct Dense-Synthetic-View (DSynView), a new synthetic dataset containing spherical layouts to evaluate our models. Our results show that MSTD outperforms MPF across image quality as well as prompt- and layout adherence. MultiPanFusion generates more diverse images but struggles to synthesize flawless foreground objects. We propose bootstrap-coupling and turning off equirectangular perspective-projection attention in the foreground as an improvement of MPF. Link to code https://github.com/sdt2i/spherical-dense-text-to-image

Brian B. Moser, Arundhati S. Shanbhag, Federico Raue et al.

Diffusion Models (DMs) have disrupted the image Super-Resolution (SR) field and further closed the gap between image quality and human perceptual preferences. They are easy to train and can produce very high-quality samples that exceed the realism of those produced by previous generative methods. Despite their promising results, they also come with new challenges that need further research: high computational demands, comparability, lack of explainability, color shifts, and more. Unfortunately, entry into this field is overwhelming because of the abundance of publications. To address this, we provide a unified recount of the theoretical foundations underlying DMs applied to image SR and offer a detailed analysis that underscores the unique characteristics and methodologies within this domain, distinct from broader existing reviews in the field. This survey articulates a cohesive understanding of DM principles and explores current research avenues, including alternative input domains, conditioning techniques, guidance mechanisms, corruption spaces, and zero-shot learning approaches. By offering a detailed examination of the evolution and current trends in image SR through the lens of DMs, this survey sheds light on the existing challenges and charts potential future directions, aiming to inspire further innovation in this rapidly advancing area.

Brian B. Moser, Federico Raue, Andreas Dengel

In image Super-Resolution (SR), relying on large datasets for training is a double-edged sword. While offering rich training material, they also demand substantial computational and storage resources. In this work, we analyze dataset pruning to solve these challenges. We introduce a novel approach that reduces a dataset to a core-set of training samples, selected based on their loss values as determined by a simple pre-trained SR model. By focusing the training on just 50\% of the original dataset, specifically on the samples characterized by the highest loss values, we achieve results comparable to or surpassing those obtained from training on the entire dataset. Interestingly, our analysis reveals that the top 5\% of samples with the highest loss values negatively affect the training process. Excluding these samples and adjusting the selection to favor easier samples further enhances training outcomes. Our work opens new perspectives to the untapped potential of dataset pruning in image SR. It suggests that careful selection of training data based on loss-value metrics can lead to better SR models, challenging the conventional wisdom that more data inevitably leads to better performance.

Brian B. Moser, Federico Raue, Tobias C. Nauen et al.

Dataset distillation has gained significant interest in recent years, yet existing approaches typically distill from the entire dataset, potentially including non-beneficial samples. We introduce a novel "Prune First, Distill After" framework that systematically prunes datasets via loss-based sampling prior to distillation. By leveraging pruning before classical distillation techniques and generative priors, we create a representative core-set that leads to enhanced generalization for unseen architectures - a significant challenge of current distillation methods. More specifically, our proposed framework significantly boosts distilled quality, achieving up to a 5.2 percentage points accuracy increase even with substantial dataset pruning, i.e., removing 80% of the original dataset prior to distillation. Overall, our experimental results highlight the advantages of our easy-sample prioritization and cross-architecture robustness, paving the way for more effective and high-quality dataset distillation.

Brian B. Moser, Ahmed Anwar, Federico Raue et al.

Traditional blind image SR methods need to model real-world degradations precisely. Consequently, current research struggles with this dilemma by assuming idealized degradations, which leads to limited applicability to actual user data. Moreover, the ideal scenario - training models on data from the targeted user base - presents significant privacy concerns. To address both challenges, we propose to fuse image SR with federated learning, allowing real-world degradations to be directly learned from users without invading their privacy. Furthermore, it enables optimization across many devices without data centralization. As this fusion is underexplored, we introduce new benchmarks specifically designed to evaluate new SR methods in this federated setting. By doing so, we employ known degradation modeling techniques from SR research. However, rather than aiming to mirror real degradations, our benchmarks use these degradation models to simulate the variety of degradations found across clients within a distributed user base. This distinction is crucial as it circumvents the need to precisely model real-world degradations, which limits contemporary blind image SR research. Our proposed benchmarks investigate blind image SR under new aspects, namely differently distributed degradation types among users and varying user numbers. We believe new methods tested within these benchmarks will perform more similarly in an application, as the simulated scenario addresses the variety while federated learning enables the training on actual degradations.

Tobias Dietz, Brian B. Moser, Tobias Nauen et al.

Dataset distillation aims to compress large datasets into compact yet highly informative subsets that preserve the training behavior of the original data. While this concept has gained traction in classification, its potential for image Super-Resolution (SR) remains largely untapped. In this work, we conduct the first systematic study of dataset distillation for SR, evaluating both pixel- and latent-space formulations. We show that a distilled dataset, occupying only 8.88% of the original size, can train SR models that retain nearly the same reconstruction fidelity as those trained on full datasets. Furthermore, we analyze how initialization strategies and distillation objectives affect efficiency, convergence, and visual quality. Our findings highlight the feasibility of SR dataset distillation and establish foundational insights for memory- and compute-efficient generative restoration models.

Ryugo Morita, Stanislav Frolov, Brian Bernhard Moser et al.

Diffusion models have enabled the generation of high-quality images with a strong focus on realism and textual fidelity. Yet, large-scale text-to-image models, such as Stable Diffusion, struggle to generate images where foreground objects are placed over a chroma key background, limiting their ability to separate foreground and background elements without fine-tuning. To address this limitation, we present a novel Training-Free Chroma Key Content Generation Diffusion Model (TKG-DM), which optimizes the initial random noise to produce images with foreground objects on a specifiable color background. Our proposed method is the first to explore the manipulation of the color aspects in initial noise for controlled background generation, enabling precise separation of foreground and background without fine-tuning. Extensive experiments demonstrate that our training-free method outperforms existing methods in both qualitative and quantitative evaluations, matching or surpassing fine-tuned models. Finally, we successfully extend it to other tasks (e.g., consistency models and text-to-video), highlighting its transformative potential across various generative applications where independent control of foreground and background is crucial.

Arundhati S. Shanbhag, Brian B. Moser, Tobias C. Nauen et al.

Diffusion models, celebrated for their generative capabilities, have recently demonstrated surprising effectiveness in image classification tasks by using Bayes' theorem. Yet, current diffusion classifiers must evaluate every label candidate for each input, creating high computational costs that impede their use in large-scale applications. To address this limitation, we propose a Hierarchical Diffusion Classifier (HDC) that exploits hierarchical label structures or well-defined parent-child relationships in the dataset. By pruning irrelevant high-level categories and refining predictions only within relevant subcategories (leaf nodes and sub-trees), HDC reduces the total number of class evaluations. As a result, HDC can speed up inference by as much as 60% while preserving and sometimes even improving classification accuracy. In summary, our work provides a tunable control mechanism between speed and precision, making diffusion-based classification more feasible for large-scale applications.

Brian B. Moser, Stanislav Frolov, Tobias C. Nauen et al.

Large-scale, pre-trained Text-to-Image (T2I) diffusion models have gained significant popularity in image generation tasks and have shown unexpected potential in image Super-Resolution (SR). However, most existing T2I diffusion models are trained with a resolution limit of 512x512, making scaling beyond this resolution an unresolved but necessary challenge for image SR. In this work, we introduce a novel approach that, for the first time, enables these models to generate 2K, 4K, and even 8K images without any additional training. Our method leverages MultiDiffusion, which distributes the generation across multiple diffusion paths to ensure global coherence at larger scales, and local degradation-aware prompt extraction, which guides the T2I model to reconstruct fine local structures according to its low-resolution input. These innovations unlock higher resolutions, allowing T2I diffusion models to be applied to image SR tasks without limitation on resolution.

Sanath Budakegowdanadoddi Nagaraju, Brian Bernhard Moser, Tobias Christian Nauen et al.

Transformer-based architectures have recently advanced the image reconstruction quality of super-resolution (SR) models. Yet, their scalability remains limited by quadratic attention costs and coarse patch embeddings that weaken pixel-level fidelity. We propose TaylorIR, a plug-and-play framework that enforces 1x1 patch embeddings for true pixel-wise reasoning and replaces conventional self-attention with TaylorShift, a Taylor-series-based attention mechanism enabling full token interactions with near-linear complexity. Across multiple SR benchmarks, TaylorIR delivers state-of-the-art performance while reducing memory consumption by up to 60%, effectively bridging the gap between fine-grained detail restoration and efficient transformer scaling.

Stanislav Frolov, Brian B. Moser, Sebastian Palacio et al.

We present ObjBlur, a novel curriculum learning approach to improve layout-to-image generation models, where the task is to produce realistic images from layouts composed of boxes and labels. Our method is based on progressive object-level blurring, which effectively stabilizes training and enhances the quality of generated images. This curriculum learning strategy systematically applies varying degrees of blurring to individual objects or the background during training, starting from strong blurring to progressively cleaner images. Our findings reveal that this approach yields significant performance improvements, stabilized training, smoother convergence, and reduced variance between multiple runs. Moreover, our technique demonstrates its versatility by being compatible with generative adversarial networks and diffusion models, underlining its applicability across various generative modeling paradigms. With ObjBlur, we reach new state-of-the-art results on the complex COCO and Visual Genome datasets.