arXiv subjects

Oliver Deussen

Publications and source records attributed to Oliver Deussen.

At least 19 recordsLinked to original sources

arXiv2026

MVWeaver: A Hierarchical Music Video Generation Agent with a Learned Song-to-Visual Bridge

Music videos are an important form of audiovisual expression in contemporary culture. They translate and extend the expressive content of songs through deliberate visual design. Existing automatic music video (MV) generation systems can generate visually plausible shots, yet often struggle with long-form coherence and song-grounded visual development. We present MVWeaver, a music video generation agent that integrates hierarchical planning with a learned song-to-visual bridge that translates song understanding into executable shot plans. The MVWeaver architecture comprises a comprehensive song analysis module, a visual planner that constructs hierarchical plans, and downstream image and video generation models that render the planned content. To equip a general-purpose LLM with MV-specific song-to-visual knowledge, we learn a bridge between song analysis and visual planning from real-MV-derived supervision and curate 1,861 real-world song--MV pairs with structured song-side, MV-side, and teacher-inferred song-to-visual rationale annotations. Using these annotations, we perform LoRA-based supervised fine-tuning (SFT) of a large language model to predict song-to-visual bridges that guide hierarchical visual planning. Our experiments demonstrate stronger song-grounded visual translation, richer visual development, and greater conceptual and shot-to-shot coherence, while ablations support the benefits of learned bridge conditioning.

cs.MM↗

arXiv2026

SNAP-tFDP: Massively Scalable Graph Layouts via Sparse Negative Sampling

Force-Directed Placement (FDP) is a widely used approach for network visualization, yet scaling it to massive graphs while preserving clear community structures remains a major computational and visual challenge. Existing approximation methods often rely on auxiliary data structures (e.g., spatial trees), which introduce substantial memory overhead; furthermore, traditional power-function-based forces frequently fail to separate dense clusters effectively. In this paper, we present a negative sampling-based algorithm that achieves O(|E|) time complexity with a low memory footprint, without requiring complex multi-level representations. In a first step, we introduce a linearly normalized degree-weighting scheme, which, combined with short-range bounded $t$-distribution forces, effectively untangles dense structures and enhances visual cluster separation. To optimize for this formulation efficiently, we introduce an edge-centric negative sampling strategy that naturally reconstructs the global degree-weighted objective. Furthermore, we design a lock-free, bundle-based parallelization scheme that leverages the sparsity of stochastic updates to achieve significant speedups while mitigating access conflicts. Comprehensive evaluations on 12 large-scale graphs demonstrate that the proposed method outperforms state-of-the-art algorithms in neighborhood preservation and cluster separation. Compared to existing baselines, our method reduces memory consumption by 72% on average and leverages simple GPU parallelism to generate a high-quality layout for a graph with 4 million nodes and 34 million edges in below 10 seconds.

cs.GR↗

arXiv2026

Structuring Line Ensembles with Path-Integrated Fidelity and Structural Inconsistency Fields

When visualizing large-scale line ensembles, trajectory continuity and visual scalability are inherently antagonistic. Trajectory-centric renderings preserve path information but rapidly degenerate into clutter as line density increases and mutual occlusion dominates. In contrast, field-based density representations enhance visibility while sacrificing structural coherence: density reflects accumulation rather than agreement, such that scalar aggregation alone cannot discriminate between consistent and conflicting configurations. Rather than replacing density-based views, we complement them with a path-integrated trajectory-fidelity measure that quantifies the agreement of each trajectory with a surrounding tensor field. By projecting this passage-centered structural support back into image space, we obtain what we call a Structural Inconsistency Field, which localizes regions where dense patterns correspond to coherent structure versus disagreement, outliers, or connectivity-induced ambiguity. Dynamic leave-one-out correction reduces self-bias in the path integral. Efficient fixed-grid updates combined with prefix-sum evaluation enable interactive analysis and iterative extraction of coherent structures. Synthetic benchmarks, scalability analyses, and real-world case studies demonstrate that, when paired with conventional density views, the proposed method disambiguates dense line patterns by exposing spatially localized coherence and structural breakdown that remain concealed in density-only representations.

cs.GR↗

arXiv2026

GLidE-SLAM: GL-Accelerated Indirect-Direct Embedded SLAM

With the growing demand for robotics, autonomous drones, and wearable extended reality systems, the deployment of Visual SLAM on embedded devices remains challenging. Tracking must sustain high frame rates while preserving compute resources for map extension and maintenance. This paper presents GLidE-SLAM, a monocular hybrid indirect-direct framework that addresses this by architectural separation: the system performs GPU-accelerated direct tracking on intermediate frames, while reserving the full indirect pipeline for map extension and global consistency. We leverage highly parallel image-alignment operations for pose-only estimation without depth optimization or map point creation, making the workload suitable for GPU offloading and freeing CPU resources for backend tasks. We implement the direct tracker using vendor-agnostic OpenGL ES~3.1 compute shaders, enabling deployment across a broader range of commodity embedded platforms without requiring CUDA support. To our knowledge, this is the first complete direct photometric pose estimator realized via compute shaders for embedded-class devices. Experiments on target platforms demonstrate up to 9$\times$ higher frame rates than the CPU-only baseline while maintaining trajectory accuracy and improving practical deployment across commodity resource-constrained hardware.

cs.RO↗

arXiv2026

Self-Reasoning Agentic Framework for Narrative Product Grid-Collage Generation

Narrative-driven product photography has become a prevalent paradigm in modern marketing, as coherent visual storytelling helps convey product value and establishes emotional engagement with consumers. However, existing image generation methods do not support structured narrative planning or cross-panel coordination, often resulting in weak storytelling and visual incoherence. In practice, narrative product photography is commonly presented as multi-grid collages, where multiple views or scenes jointly communicate a product narrative. To ensure visual consistency across grids and aesthetic harmony of the overall composition, we generate the collage as a single unified image rather than composing independently synthesized panels. We propose a self-reasoning agentic framework for narrative product grid collage generation. Given a product packshot and its name, the system first constructs a Product Narrative Framework that explicitly represents the product's identity, usage context, and situational environment, and translates it into complementary grids governed by a shared visual style. Constraint-aware prompts are then compiled and fed to a generation model that synthesizes the collage jointly. The generated output is evaluated on both content validity and photography quality, with explicit gates determining whether to proceed or refine. When evaluation fails, the system performs failure attribution and applies targeted refinement, enabling progressive improvement through iterative self-reflection. Experiments demonstrate that our framework consistently improves aesthetic quality, narrative richness, and visual coherence, compared to direct prompting baselines.

cs.CV↗

arXiv2026

SongEcho: Towards Cover Song Generation via Instance-Adaptive Element-wise Linear Modulation

Cover songs constitute a vital aspect of musical culture, preserving the core melody of an original composition while reinterpreting it to infuse novel emotional depth and thematic emphasis. Although prior research has explored the reinterpretation of instrumental music through melody-conditioned text-to-music models, the task of cover song generation remains largely unaddressed. In this work, we reformulate our cover song generation as a conditional generation, which simultaneously generates new vocals and accompaniment conditioned on the original vocal melody and text prompts. To this end, we present SongEcho, which leverages Instance-Adaptive Element-wise Linear Modulation (IA-EiLM), a framework that incorporates controllable generation by improving both conditioning injection mechanism and conditional representation. To enhance the conditioning injection mechanism, we extend Feature-wise Linear Modulation (FiLM) to an Element-wise Linear Modulation (EiLM), to facilitate precise temporal alignment in melody control. For conditional representations, we propose Instance-Adaptive Condition Refinement (IACR), which refines conditioning features by interacting with the hidden states of the generative model, yielding instance-adaptive conditioning. Additionally, to address the scarcity of large-scale, open-source full-song datasets, we construct Suno70k, a high-quality AI song dataset enriched with comprehensive annotations. Experimental results across multiple datasets demonstrate that our approach generates superior cover songs compared to existing methods, while requiring fewer than 30% of the trainable parameters. The code, dataset, and demos are available at https://github.com/lsfhuihuiff/SongEcho_ICLR2026.

cs.SD↗

arXiv2026

Beyond Pixels: Visual Metaphor Transfer via Schema-Driven Agentic Reasoning

A visual metaphor constitutes a high-order form of human creativity, employing cross-domain semantic fusion to transform abstract concepts into impactful visual rhetoric. Despite the remarkable progress of generative AI, existing models remain largely confined to pixel-level instruction alignment and surface-level appearance preservation, failing to capture the underlying abstract logic necessary for genuine metaphorical generation. To bridge this gap, we introduce the task of Visual Metaphor Transfer (VMT), which challenges models to autonomously decouple the "creative essence" from a reference image and re-materialize that abstract logic onto a user-specified target subject. We propose a cognitive-inspired, multi-agent framework that operationalizes Conceptual Blending Theory (CBT) through a novel Schema Grammar ("G"). This structured representation decouples relational invariants from specific visual entities, providing a rigorous foundation for cross-domain logic re-instantiation. Our pipeline executes VMT through a collaborative system of specialized agents: a perception agent that distills the reference into a schema, a transfer agent that maintains generic space invariance to discover apt carriers, a generation agent for high-fidelity synthesis and a hierarchical diagnostic agent that mimics a professional critic, performing closed-loop backtracking to identify and rectify errors across abstract logic, component selection, and prompt encoding. Extensive experiments and human evaluations demonstrate that our method significantly outperforms SOTA baselines in metaphor consistency, analogy appropriateness, and visual creativity, paving the way for automated high-impact creative applications in advertising and media. Project page with source code and self-contained skills is at https://yuci-gpt.github.io/Beyond-Pixels/.

cs.CV↗

arXiv2025

Enhancing Line Density Plots with Outlier Control and Bin-based Illumination

Density plots effectively summarize large numbers of points, which would otherwise lead to severe overplotting in, for example, a scatter plot. However, when applied to line-based datasets, such as trajectories or time series, density plots alone are insufficient, as they disrupt path continuity, obscuring smooth trends and rare anomalies. We propose a bin-based illumination model that decouples structure from density to enhance flow and reveal sparse outliers while preserving the original colormap. We introduce a bin-based outlierness metric to rank trajectories. Guided by this ranking, we construct a structural normal map and apply locally-adaptive lighting in the luminance channel to highlight chosen patterns -- from dominant trends to atypical paths -- with acceptable color distortion. Our interactive method enables analysts to prioritize main trends, focus on outliers, or strike a balance between the two. We demonstrate our method on several real-world datasets, showing it reveals details missed by simpler alternatives, achieves significantly lower CIEDE2000 color distortion than standard shading, and supports interactive updates for up to 10,000 lines.

cs.GR↗

arXiv2025

Neural Image Abstraction Using Long Smoothing B-Splines

We integrate smoothing B-splines into a standard differentiable vector graphics (DiffVG) pipeline through linear mapping, and show how this can be used to generate smooth and arbitrarily long paths within image-based deep learning systems. We take advantage of derivative-based smoothing costs for parametric control of fidelity vs. simplicity tradeoffs, while also enabling stylization control in geometric and image spaces. The proposed pipeline is compatible with recent vector graphics generation and vectorization methods. We demonstrate the versatility of our approach with four applications aimed at the generation of stylized vector graphics: stylized space-filling path generation, stroke-based image abstraction, closed-area image abstraction, and stylized text generation.

cs.GR↗

arXiv2025

Co-Located VR with Hybrid SLAM-based HMD Tracking and Motion Capture Synchronization

We introduce a multi-user VR co-location framework that synchronizes users within a shared virtual environment aligned to physical space. Our approach combines a motion capture system with SLAM-based inside-out tracking to deliver smooth, high-framerate, low-latency performance. Previous methods either rely on continuous external tracking, which introduces latency and jitter, or on one-time calibration, which cannot correct drift over time. In contrast, our approach combines the responsiveness of local HMD SLAM tracking with the flexibility to realign to an external source when needed. It also supports real-time pose sharing across devices, ensuring consistent spatial alignment and engagement between users. Our evaluation demonstrates that our framework achieves the spatial accuracy required for natural multi-user interaction while offering improved comfort, scalability, and robustness over existing co-located VR solutions.

cs.RO↗

arXiv2025

Neighborhood-Preserving Voronoi Treemaps

Voronoi treemaps are used to depict nodes and their hierarchical relationships simultaneously. However, in addition to the hierarchical structure, data attributes, such as co-occurring features or similarities, frequently exist. Examples include geographical attributes like shared borders between countries or contextualized semantic information such as embedding vectors derived from large language models. In this work, we introduce a Voronoi treemap algorithm that leverages data similarity to generate neighborhood-preserving treemaps. First, we extend the treemap layout pipeline to consider similarity during data preprocessing. We then use a Kuhn-Munkres matching of similarities to centroidal Voronoi tessellation (CVT) cells to create initial Voronoi diagrams with equal cell sizes for each level. Greedy swapping is used to improve the neighborhoods of cells to match the data's similarity further. During optimization, cell areas are iteratively adjusted to their respective sizes while preserving the existing neighborhoods. We demonstrate the practicality of our approach through multiple real-world examples drawn from infographics and linguistics. To quantitatively assess the resulting treemaps, we employ treemap metrics and measure neighborhood preservation.

cs.GR↗

arXiv2025

Image-driven Robot Drawing with Rapid Lognormal Movements

Large image generation and vision models, combined with differentiable rendering technologies, have become powerful tools for generating paths that can be drawn or painted by a robot. However, these tools often overlook the intrinsic physicality of the human drawing/writing act, which is usually executed with skillful hand/arm gestures. Taking this into account is important for the visual aesthetics of the results and for the development of closer and more intuitive artist-robot collaboration scenarios. We present a method that bridges this gap by enabling gradient-based optimization of natural human-like motions guided by cost functions defined in image space. To this end, we use the sigma-lognormal model of human hand/arm movements, with an adaptation that enables its use in conjunction with a differentiable vector graphics (DiffVG) renderer. We demonstrate how this pipeline can be used to generate feasible trajectories for a robot by combining image-driven objectives with a minimum-time smoothing criterion. We demonstrate applications with generation and robotic reproduction of synthetic graffiti as well as image abstraction.

cs.RO↗

arXiv2025

In-Context Brush: Zero-shot Customized Subject Insertion with Context-Aware Latent Space Manipulation

Recent advances in diffusion models have enhanced multimodal-guided visual generation, enabling customized subject insertion that seamlessly "brushes" user-specified objects into a given image guided by textual prompts. However, existing methods often struggle to insert customized subjects with high fidelity and align results with the user's intent through textual prompts. In this work, we propose "In-Context Brush", a zero-shot framework for customized subject insertion by reformulating the task within the paradigm of in-context learning. Without loss of generality, we formulate the object image and the textual prompts as cross-modal demonstrations, and the target image with the masked region as the query. The goal is to inpaint the target image with the subject aligning textual prompts without model tuning. Building upon a pretrained MMDiT-based inpainting network, we perform test-time enhancement via dual-level latent space manipulation: intra-head "latent feature shifting" within each attention head that dynamically shifts attention outputs to reflect the desired subject semantics and inter-head "attention reweighting" across different heads that amplifies prompt controllability through differential attention prioritization. Extensive experiments and applications demonstrate that our approach achieves superior identity preservation, text alignment, and image quality compared to existing state-of-the-art methods, without requiring dedicated training or additional data collection.

cs.CV↗

arXiv2025

IP-Prompter: Training-Free Theme-Specific Image Generation via Dynamic Visual Prompting

The stories and characters that captivate us as we grow up shape unique fantasy worlds, with images serving as the primary medium for visually experiencing these realms. Personalizing generative models through fine-tuning with theme-specific data has become a prevalent approach in text-to-image generation. However, unlike object customization, which focuses on learning specific objects, theme-specific generation encompasses diverse elements such as characters, scenes, and objects. Such diversity also introduces a key challenge: how to adaptively generate multi-character, multi-concept, and continuous theme-specific images (TSI). Moreover, fine-tuning approaches often come with significant computational overhead, time costs, and risks of overfitting. This paper explores a fundamental question: Can image generation models directly leverage images as contextual input, similarly to how large language models use text as context? To address this, we present IP-Prompter, a novel training-free TSI generation method. IP-Prompter introduces visual prompting, a mechanism that integrates reference images into generative models, allowing users to seamlessly specify the target theme without requiring additional training. To further enhance this process, we propose a Dynamic Visual Prompting (DVP) mechanism, which iteratively optimizes visual prompts to improve the accuracy and quality of generated images. Our approach enables diverse applications, including consistent story generation, character design, realistic character generation, and style-guided image generation. Comparative evaluations against state-of-the-art personalization methods demonstrate that IP-Prompter achieves significantly better results and excels in maintaining character identity preserving, style consistency and text alignment, offering a robust and flexible solution for theme-specific image generation.

cs.CV↗

arXiv2025

Mesh2SLAM in VR: A Fast Geometry-Based SLAM Framework for Rapid Prototyping in Virtual Reality Applications

SLAM is a foundational technique with broad applications in robotics and AR/VR. SLAM simulations evaluate new concepts, but testing on resource-constrained devices, such as VR HMDs, faces challenges: high computational cost and restricted sensor data access. This work proposes a sparse framework using mesh geometry projections as features, which improves efficiency and circumvents direct sensor data access, advancing SLAM research as we demonstrate in VR and through numerical evaluation.

cs.RO↗

arXiv2024

HeadRouter: A Training-free Image Editing Framework for MM-DiTs by Adaptively Routing Attention Heads

Diffusion Transformers (DiTs) have exhibited robust capabilities in image generation tasks. However, accurate text-guided image editing for multimodal DiTs (MM-DiTs) still poses a significant challenge. Unlike UNet-based structures that could utilize self/cross-attention maps for semantic editing, MM-DiTs inherently lack support for explicit and consistent incorporated text guidance, resulting in semantic misalignment between the edited results and texts. In this study, we disclose the sensitivity of different attention heads to different image semantics within MM-DiTs and introduce HeadRouter, a training-free image editing framework that edits the source image by adaptively routing the text guidance to different attention heads in MM-DiTs. Furthermore, we present a dual-token refinement module to refine text/image token representations for precise semantic guidance and accurate region expression. Experimental results on multiple benchmarks demonstrate HeadRouter's performance in terms of editing fidelity and image quality.

cs.CV↗

arXiv2024

Newton Losses: Using Curvature Information for Learning with Differentiable Algorithms

When training neural networks with custom objectives, such as ranking losses and shortest-path losses, a common problem is that they are, per se, non-differentiable. A popular approach is to continuously relax the objectives to provide gradients, enabling learning. However, such differentiable relaxations are often non-convex and can exhibit vanishing and exploding gradients, making them (already in isolation) hard to optimize. Here, the loss function poses the bottleneck when training a deep neural network. We present Newton Losses, a method for improving the performance of existing hard to optimize losses by exploiting their second-order information via their empirical Fisher and Hessian matrices. Instead of training the neural network with second-order techniques, we only utilize the loss function's second-order information to replace it by a Newton Loss, while training the network with gradient descent. This makes our method computationally efficient. We apply Newton Losses to eight differentiable algorithms for sorting and shortest-paths, achieving significant improvements for less-optimized differentiable algorithms, and consistent improvements, even for well-optimized differentiable algorithms.

cs.LG↗

arXiv2024

UADAPy: An Uncertainty-Aware Visualization and Analysis Toolbox

Current research provides methods to communicate uncertainty and adapts classical algorithms of the visualization pipeline to take the uncertainty into account. Various existing visualization frameworks include methods to present uncertain data but do not offer transformation techniques tailored to uncertain data. Therefore, we propose a software package for uncertainty-aware data analysis in Python (UADAPy) offering methods for uncertain data along the visualization pipeline. We aim to provide a platform that is the foundation for further integration of uncertainty algorithms and visualizations. It provides common utility functionality to support research in uncertainty-aware visualization algorithms and makes state-of-the-art research results accessible to the end user. The project is available at https://github.com/UniStuttgart-VISUS/uadapy.

cs.HC↗