Eurographics Digital Library
Not a member yet
17121 research outputs found
Sort by
DiffNEG: A Differentiable Rasterization Framework for Online Aiming Optimization in Solar Power Tower Systems
No full textInverse rendering aims to infer scene parameters from observed images. In Solar Power Tower (SPT) systems, this corresponds to an aiming optimization problem-adjusting heliostats' orientations to shape the radiative flux density distribution (RFDD) on the receiver to conform to a desired distribution. The SPT system is widely favored in the field of renewable energy, where aiming optimization is crucial for ensuring its thermal efficiency and safety. However, traditional aiming optimization methods are inefficient and fail to meet online demands. In this paper, a novel optimization approach, DiffNEG, is proposed. DiffNEG introduces a differentiable rasterization method to model the reflected radiative flux of each heliostat as an elliptical Gaussian distribution. It leverages data-driven techniques to enhance simulation accuracy and employs automatic differentiation combined with gradient descent to achieve online, gradient-guided optimization in a continuous solution space. Experiments on a real large-scale heliostat field with nearly 30,000 heliostats demonstrate that DiffNEG can optimize within 10 seconds, improving efficiency by one order of magnitude compared to the latest DiffMCRT method and by three orders of magnitude compared to traditional heuristic methods, while also exhibiting superior robustness under both steady and transient state.Computer Graphics ForumDifferentiable Rendering44
Differentiable Block Compression for Neural Texture
No full textIn real-time rendering, neural network models using neural textures (texture-form neural features) are increasingly applied. For high-memory scenarios like film-grade games, reducing neural texture memory overhead is critical. While neural textures can use hardware-accelerated block compression for memory savings and leverage hardware texture filtering for performance, mainstream block compression encoders only aim to minimize compression errors. This design may significantly increase neural network model loss.We propose a novel differentiable block compression (DBC) framework that integrates encoding and decoding into neural network optimization training. Compared with direct compression by mainstream encoders, end-to-end trained neural textures reduce model loss. The framework first enables differentiable encoding computation, then uses a compressionerror- based stochastic sampling strategy for encoding configuration selection. A Mixture of Partitions (MoP) module is introduced to reduce computational costs from multiple partition configurations. As DBC employs native block compression formats, inference maintains real-time performance.Eurographics Symposium on RenderingDifferentiable Renderin
Sharpening Your Density Fields: Spiking Neuron Aided Fast Geometry Learning
No full textNeural Radiance Fields (NeRF) have achieved remarkable progress in neural rendering. Extracting geometry from NeRF typically relies on the Marching Cubes algorithm, which uses a hand-crafted threshold to define the level set. However, this threshold-based approach requires laborious and scenario-specific tuning, limiting its practicality for real-world applications. In this work, we seek to enhance the efficiency of this method during the training time. To this end, we introduce a spiking neuron mechanism that dynamically adjusts the threshold, eliminating the need for manual selection. Despite its promise, directly training with the spiking neuron often results in model collapse and noisy outputs. To overcome these challenges, we propose a round-robin strategy that stabilizes the training process and enables the geometry network to achieve a sharper and more precise density distribution with minimal computational overhead. We validate our approach through extensive experiments on both synthetic and real-world datasets. The results show that our method significantly improves the performance of threshold-based techniques, offering a more robust and efficient solution for NeRF geometry extraction.Eurographics Symposium on RenderingDifferentiable Renderin
Fully Automated Quantification of Synaptic Locations in Multi-channel Drosophila Photoreceptor Microscopy Data
No full textThe workload posed by image analysis remains a major bottleneck for advances across the life sciences. To address this challenge, we have developed a fully automated workflow for processing complex 3D multi-channel microscopy images. Specifically, our workflow addresses the analysis of photoreceptor synapses in confocal images of the Drosophila melanogaster optic lobe. The workflow consists of multiple stages, combining traditional and machine learning-based approaches for image analysis and visual computing. It performs segmentation of brain regions, photoreceptor instance identification, and precise localization of synapses. The key novelty of the workflow is an automatic alignment of synapses into a cylindrical reference coordinate system, enabling comparative synaptic analysis across photoreceptors. To demonstrate the workflow's applicability, preliminary biological results and their interpretation based on 50 images are presented. While the workflow is still being improved further, here, we showcase its capacity for efficient and objective data processing for high-throughput neurobiological analyses.Eurographics Workshop on Visual Computing for Biology and MedicineSession
Robotic Painting using Semantic Image Abstraction
No full textWe present a novel image segmentation and abstraction pipeline tailored to robot painting applications. We address the unique challenges of realizing digital abstractions as physical artistic renderings. Our approach generates adaptive, semantics-based abstractions that balance aesthetic appeal, structural coherence, and practical constraints inherent to robotic systems. By integrating panoptic segmentation with color-based over-segmentation, we partition images into meaningful regions corresponding to semantic objects while providing customizable abstraction levels we optimize for robotic realization. We employ saliency maps and color difference metrics to support automatic parameter selection to guide a merging process that detects and preserves critical object boundaries while simplifying less salient areas. Graph-based community detection further refines the abstraction by grouping regions based on local connectivity and semantic coherence. These abstractions enable robotic systems to create paintings on real canvases with a controlled level of detail and abstraction.ACM/EG Expressive Symposium - WICED: Eurographics Workshop on Intelligent Cinematography and Editing - Artworks, Posters, DemosPoster
Optimizing Staircase Motifs in Biofabric Network Layouts
No full textBiofabric is a novel method for network visualization, with promising potential to highlight specific network features. Recent studies emphasize the importance of staircase motifs - equivalent to fans or stars in node-link diagrams - within Biofabric. However, to effectively showcase these motifs, we need to formulate specialized layout algorithms. This paper introduces a method to compute optimal layouts for Biofabric, focusing on maximizing staircase formation. We present an Integer Linear Programming (ILP) model for this task and evaluate its performance in terms of scalability and output quality against a leading heuristic method, Degreecending. Our results demonstrate that the ILP approach identifies significantly more, and often longer, staircases compared to Degreecending, albeit with the trade-off of higher computation times. Our supplemental material, including a full copy of the paper, code, and results, is available on osf.io.Computer Graphics ForumHonourable Mentio
Pie Chart Glyph Visualization of Uncertain Connected Components
No full textEdges of graphs are often associated with uncertainty. The inherent uncertainty of the data also induces uncertainty in derived graph attributes such as connected components. Even for planar graphs, visualizing the connected components in the graph embedding while encoding their uncertainty imposes challenges due to overlap. We present a visual encoding for uncertain connected components in a planar graph embedding. The underlying model does not require matching or assumptions on the overlap of the components and emphasizes uncertain boundary regions. We discuss different design options and show the applicability of our approach based on synthetic data and real-world data on force networks in granular materials.EuroVis 2025 - PostersPoster
Real-Time Secondary Animation with Spring Decomposed Skinning
No full textWe present a framework to integrate secondary motion into the existing animation pipelines. Skinning provides fast computation for real-time animation and intuitive control over the deformation. Despite the benefits, traditional skinning methods lack secondary dynamics such as the jiggling of fat tissues. We address the rigidity of skinning methods by physically simulating the deformation handles with spring forces. Most studies introduce secondary motion into skinning by employing FEM simulation on volumetric mesh vertices, coupling their computational complexity with mesh resolution. Unlike these approaches, we do not require any volumetric mesh input. Our method scales to higher mesh resolutions by directly simulating deformation handles. The simulated handles, namely the spring bones, enrich rigid skinning deformation with a diverse range of secondary animation for subjects including rigid bodies, elastic bodies, soft tissues, and cloth simulation. In essence, we leverage the benefits of physical simulations in the scope of deformation handles to achieve controllable real-time dynamics on a wide range of subjects while remaining compatible with existing skinning pipelines. Our method avoids tetrahedral remeshing and it is significantly faster compared to FEM-based volumetric mesh simulations.Computer Graphics ForumAnimation and Morphing44
Textile Photography with Pixel Shift Multi Shooting for Merdeka Textile Museum Archival Project
No full textFor the purposes of this paper, we will be discussing and presenting workflow related to the textile digitization processes for the upcoming Merdeka Textile Museum (MTM), Malaysia. This collection of textiles is part of the personal collection of the late Sharifah Azah Syed Mohammad Alsagoff or fondly known as Azah Aziz who is renowned for championing knowledge of Malay textiles and costumes. These textiles date back to the 1900s and continue into the 2000s, some of which are fragile and decaying due to age and natural conditions. All textiles gathered are of those associated with the Malay world, which employ a variety of production methods such as weaving, embroidery and printing on cotton, silk and other materials in their creation. Taking into consideration the fragility and intricacy of these textiles, parts of the digitization process are impacted because they present a variety of challenges, for instance, the reflective nature of the golden yarn under direct light source. Our paper presentation will cover the workflow, beginning with the handling of the textiles and continuing through to the lighting and camera setup. We will discuss the technical decisions that we made to use the Sony camera for the Pixel Shift Multi Shooting techniques. In addition, the paper will also discuss the post-processing works that were performed on the files that were generated in order to get them ready for archiving, both online and offline as part of the digital heritage preservation causes in collaboration with MTM. The museum, which is a project of the subsidiary of Permodalan Nasional Bhd (PNB) known as PNB Merdeka Ventures Sdn. Bhd. will house 240 pieces of textiles and costumes, along with 69 pieces of jewelry that belonged to Azah Aziz. Through this collection as well as references to traditional Malay literature, the MTM will offer a distinctive curatorial perspective on textiles from around the world that are of Malay origin for public knowledge and consumption as part of its efforts to promote and preserve Malay culture and heritage.Digital HeritageDigitization, Documentation, and Dissemination Workflow
Two-shot Shape and SVBRDF Reconstruction of Human Faces with Albedo-Conditioned Diffusion
No full textReconstructing 3D human heads with relightability has been a long-standing research problem. Most methods either require a complicated hardware setup for multiview capture or involve fitting a pre-learned morphable model, resulting in a loss of details. In our work, we present a two-step deep learning method that directly predicts the shape and SVBRDF of a subject's face given two images taken from each side of the face. We enhance SVBRDF prediction by first estimating the diffuse and specular albedo in image space, then generating texture maps in UV-space with a generative model. We also learn a 2D position map in UVspace for 3D geometry, eliminating the need for a morphable model. Contrary to single-image facial reconstruction methods, we obtain clear measurements on both sides of the face with two images. Our method outperforms state-of-the-art methods when rendering faces at extreme angles and provides texture maps that are directly usable in most rendering systems.Eurographics 2025 - Short PapersShort Paper