EG2025

Permanent URI for this community

https://diglib.eg.org/handle/10.2312/3607134

Browse

Now showing 1 - 20 of 141

Synchronized Multi-Frame Diffusion for Temporally Consistent Video Stylization
(The Eurographics Association and John Wiley & Sons Ltd., 2025) Xie, Minshan; Liu, Hanyuan; Li, Chengze; Wong, Tien-Tsin; Bousseau, Adrien; Day, Angela
Text-guided video-to-video stylization transforms the visual appearance of a source video to a different appearance guided on textual prompts. Existing text-guided image diffusion models can be extended for stylized video synthesis. However, they struggle to generate videos with both highly detailed appearance and temporal consistency. In this paper, we propose a synchronized multi-frame diffusion framework to maintain both the visual details and the temporal consistency. Frames are denoised in a synchronous fashion, and more importantly, information of different frames is shared since the beginning of the denoising process. Such information sharing ensures that a consensus, in terms of the overall structure and color distribution, among frames can be reached in the early stage of the denoising process before it is too late. The optical flow from the original video serves as the connection, and hence the venue for information sharing, among frames. We demonstrate the effectiveness of our method in generating high-quality and diverse results in extensive experiments. Our method shows superior qualitative and quantitative results compared to state-of-the-art video editing methods.
Efficient Perspective-Correct 3D Gaussian Splatting Using Hybrid Transparency
(The Eurographics Association and John Wiley & Sons Ltd., 2025) Hahlbohm, Florian; Friederichs, Fabian; Weyrich, Tim; Franke, Linus; Kappel, Moritz; Castillo, Susana; Stamminger, Marc; Eisemann, Martin; Magnor, Marcus; Bousseau, Adrien; Day, Angela
3D Gaussian Splats (3DGS) have proven a versatile rendering primitive, both for inverse rendering as well as real-time exploration of scenes. In these applications, coherence across camera frames and multiple views is crucial, be it for robust convergence of a scene reconstruction or for artifact-free fly-throughs. Recent work started mitigating artifacts that break multi-view coherence, including popping artifacts due to inconsistent transparency sorting and perspective-correct outlines of (2D) splats. At the same time, real-time requirements forced such implementations to accept compromises in how transparency of large assemblies of 3D Gaussians is resolved, in turn breaking coherence in other ways. In our work, we aim at achieving maximum coherence, by rendering fully perspective-correct 3D Gaussians while using a high-quality approximation of accurate blending, hybrid transparency, on a per-pixel level, in order to retain real-time frame rates. Our fast and perspectively accurate approach for evaluation of 3D Gaussians does not require matrix inversions, thereby ensuring numerical stability and eliminating the need for special handling of degenerate splats, and the hybrid transparency formulation for blending maintains similar quality as fully resolved per-pixel transparencies at a fraction of the rendering costs. We further show that each of these two components can be independently integrated into Gaussian splatting systems. In combination, they achieve up to 2× higher frame rates, 2× faster optimization, and equal or better image quality with fewer rendering artifacts compared to traditional 3DGS on common benchmarks.
VortexTransformer: End-to-End Objective Vortex Detection in 2D Unsteady Flow Using Transformers
(The Eurographics Association and John Wiley & Sons Ltd., 2025) Zhang, Xingdi; Rautek, Peter; Hadwiger, Markus; Bousseau, Adrien; Day, Angela
Vortex structures play a pivotal role in understanding complex fluid dynamics, yet defining them rigorously remains challenging. One hard criterion is that a vortex detector must be objective, i.e., it needs to be indifferent to reference frame transformations. We propose VortexTransformer, a novel deep learning approach using point transformer architectures to directly extract vortex structures from pathlines. Unlike traditional methods that rely on grid-based velocity fields in the Eulerian frame, our approach operates entirely on a Lagrangian representation of the flow field (i.e., pathlines), enabling objective identification of both strong and weak vortex structures. To train VortexTransformer, we generate a large synthetic dataset using parametric flow models to simulate diverse vortex configurations, ensuring a robust ground truth. We compare our method against CNN and UNet architectures, applying the trained models to real-world flow datasets. VortexTransformer is an end-to-end detector, which means that reference frame transformations as well as vortex detection are handled implicitly by the network, demonstrating the ability to extract vortex boundaries without the need for parameters such as arbitrary thresholds, or an explicit definition of a vortex. Our method offers a new approach to determining objective vortex labels by using the objective pairwise distances of material points for vortex detection and is adaptable to various flow conditions.
Eigenvalue Blending for Projected Newton
(The Eurographics Association and John Wiley & Sons Ltd., 2025) Cheng, Yuan-Yuan; Liu, Ligang; Fu, Xiao-Ming; Bousseau, Adrien; Day, Angela
We propose a novel method to filter eigenvalues for projected Newton. Central to our method is blending the clamped and absolute eigenvalues to adaptively compute the modified Hessian matrix. To determine the blending coefficients, we rely on (1) a key observation and (2) an objective function descent constraint. The observation is that if the quadratic form defined by the Hessian matrix maps the descent direction to a negative real number, the decrease in the objective function is limited. The constraint is that our eigenvalue filtering leads to more reduction in objective function than the absolute eigenvalue filtering [CLL∗24] in the case of second-order Taylor approximation. Our eigenvalue blending is easy to implement and leads to fewer optimization iterations than the state-of-the-art eigenvalue filtering methods.
Fast Sphere Tracing of Procedural Volumetric Noise for very Large and Detailed Scenes
(The Eurographics Association and John Wiley & Sons Ltd., 2025) Moinet, Mathéo; Neyret, Fabrice; Bousseau, Adrien; Day, Angela
Real-time walk through very large and detailed scenes is a challenge for both content design, data management, and rendering, and requires LOD to handle the scale range. In the case of partly stochastic content (clouds, cosmic dust, fire, terrains, etc.), proceduralism allows arbitrary large and detailed scenes with no or little storage and offers embedded LOD, but the rendering gets even costlier. In this paper, we propose to boost the performance of Fractional Brownian Motion (FBM)-based noise rendering (e.g., 3D Perlin noise, hypertextures) in two ways: improving the stepping efficiency of Sphere Tracing of general Signed Distance Functions (SDF) considering the first and second derivatives, and treating cascaded sums such as FBM as nested bounding volumes. We illustrate this on various scenes made of either opaque material, constant semi-transparent material, or non-constant (i.e., full volumetric inside) material, including animated content - thanks to on-the-fly proceduralism. We obtain real-time performances with speedups up to 12-folds on opaque or constant semi-transparent scenes compared to classical Sphere tracing, and up to 2-folds (through empty space skipping optimization) on non-constant density volumetric scenes.
Multi-Objective Packing of 3D Objects into Arbitrary Containers
(The Eurographics Association, 2025) Meißenhelter, Hermann; Weller, Rene; Zachmann, Gabriel; Ceylan, Duygu; Li, Tzu-Mao
Packing problems arise in numerous real-world applications and often take diverse forms. We focus on the relatively underexplored task of packing a set of arbitrary 3D objects-drawn from a predefined distribution-into a single arbitrary 3D container. We simultaneously optimize two potentially conflicting objectives: maximizing the packed volume and maintaining sufficient spacing among objects of the same type to prevent clustering. We present an algorithm to compute solutions to this challenging problem heuristically. Our approach is a flexible two-tier pipeline that computes and refines an initial arrangement. Our results confirm that this approach achieves dense packings across various objects and container shapes.
Neural Face Skinning for Mesh-agnostic Facial Expression Cloning
(The Eurographics Association and John Wiley & Sons Ltd., 2025) Cha, Sihun; Yoon, Serin; Seo, Kwanggyoon; Noh, Junyong; Bousseau, Adrien; Day, Angela
Accurately retargeting facial expressions to a face mesh while enabling manipulation is a key challenge in facial animation retargeting. Recent deep-learning methods address this by encoding facial expressions into a global latent code, but they often fail to capture fine-grained details in local regions. While some methods improve local accuracy by transferring deformations locally, this often complicates overall control of the facial expression. To address this, we propose a method that combines the strengths of both global and local deformation models. Our approach enables intuitive control and detailed expression cloning across diverse face meshes, regardless of their underlying structures. The core idea is to localize the influence of the global latent code on the target mesh. Our model learns to predict skinning weights for each vertex of the target face mesh through indirect supervision from predefined segmentation labels. These predicted weights localize the global latent code, enabling precise and region-specific deformations even for meshes with unseen shapes. We supervise the latent code using Facial Action Coding System (FACS)-based blendshapes to ensure interpretability and allow straightforward editing of the generated animation. Through extensive experiments, we demonstrate improved performance over state-of-the-art methods in terms of expression fidelity, deformation transfer accuracy, and adaptability across diverse mesh structures.
Harnessing Artificial Intelligence to Expedite Content Creation for the Development of eXtended Reality Experiences
(The Eurographics Association, 2025) Freitas, André; Borges, João; Marques, Bernardo; Dias, Paulo; Santos, Beatriz Sousa; Kuffner dos Anjos, Rafael; Rodriguez Echavarria, Karina
Despite eXtended Reality (XR) many benefits and demonstrated potential, the process of creating content specifically designed for distinct applications remains time-intensive and resource-demanding, hindering broader adoption. This study presents a student-driven project that investigates the role of Artificial Intelligence (AI) in streamlining the content creation process of 3D models. The proposed solution enables a user, equipped with an XR headset to use gesture recognition and perform a query via a text prompt, or as an alternative, to use voice recognition. Afterward, a request will be made to an API, which will generate the 3D model. Finally, the model will be added to a local library and become accessible in the XR environment, allowing users to manipulate, position, and other features. Initial findings highlight both opportunities and challenges, confirming it is already possible to integrate AI into a game engine with interesting results, while also showcasing that additional work is still necessary for obtaining more detailed and complex 3D models moving forward.
A Gaze Prediction Model for Task-Oriented Virtual Reality
(The Eurographics Association, 2025) Mammou, Konstantina; Mania, Katerina; Günther, Tobias; Montazeri, Zahra
In this work, we present a gaze prediction model for Virtual Reality task-oriented environments. Unlike past work which focuses on gaze prediction for specific tasks, we investigate the role and potential of temporal continuity in enabling accurate predictions in diverse task categories. The model reduces input complexity while maintaining high prediction accuracy. Evaluated on the OpenNEEDS dataset, it significantly outperforms baseline methods. The model demonstrates strong potential for integration into gaze-based VR interactions and foveated rendering pipelines. Future work will focus on runtime optimization and expanding evaluation across diverse VR scenarios.
Neural Two-Level Monte Carlo Real-Time Rendering
(The Eurographics Association and John Wiley & Sons Ltd., 2025) Dereviannykh, Mikhail; Klepikov, Dmitrii; Hanika, Johannes; Dachsbacher, Carsten; Bousseau, Adrien; Day, Angela
We introduce an efficient Two-Level Monte Carlo (subset of Multi-Level Monte Carlo, MLMC) estimator for real-time rendering of scenes with global illumination. Using MLMC we split the shading integral into two parts: the radiance cache integral and the residual error integral that compensates for the bias of the first one. For the first part, we developed the Neural Incident Radiance Cache (NIRC) leveraging the power of tiny neural networks [MRNK21] as a building block, which is trained on the fly. The cache is designed to provide a fast and reasonable approximation of the incident radiance: an evaluation takes 2-25× less compute time than a path tracing sample. This enables us to estimate the radiance cache integral with a high number of samples and by this achieve faster convergence. For the residual error integral, we compute the difference between the NIRC predictions and the unbiased path tracing simulation. Our method makes no assumptions about the geometry, materials, or lighting of a scene and has only few intuitive hyper-parameters. We provide a comprehensive comparative analysis in different experimental scenarios. Since the algorithm is trained in an on-line fashion, it demonstrates significant noise level reduction even for dynamic scenes and can easily be combined with other noise reduction techniques.
Traditional and Neural Order-Independent Transparency
(The Eurographics Association, 2025) Tsopouridis, Grigoris; Georgiou-Mousses, Christos; Fudos, Ioannis; Corrigan, David; Franke, Tobias Alexander; Mantiuk, Rafal; Hildebrandt, Klaus
Order independent transparency (OIT) is a technique in computer graphics that allows for accurate rendering of transparent objects without the need to sort them in a specific order based on their depth. Traditional transparency methods often suffer from artifacts and inaccuracies due to this sorting process, especially in complex scenes with many overlapping transparent surfaces. OIT is important because it provides a more visually correct representation of transparent materials, ensuring that colors mix accurately and that all elements are rendered consistently, regardless of their draw order. This enhances realism in applications such as video games, simulations, and visual effects in films. The tutorial will provide an overview of traditional (exact, approximate and hybrid) and deep learning approaches to OIT and examine their scope, performance and accuracy.
Screentone-Preserved Manga Retargeting
(The Eurographics Association and John Wiley & Sons Ltd., 2025) Xie, Minshan; Xia, Menghan; Li, Chengze; Liu, Xueting; Wong, Tien-Tsin; Bousseau, Adrien; Day, Angela
As a popular comic style, manga offers a unique impression by utilizing a rich set of bitonal patterns, or screentones, for illustration. However, screentones can easily be degraded when manga is resized in terms of aspect ratio and resolution for manga re-layout and e-manga migration applications. To tackle this problem, we propose the first automatic manga retargeting method that synthesizes a retargeted manga image while preserving the prominent structure and fine screentone intended by the manga artist. While modern natural photo retargeting methods can achieve prominent structure preservation, preserving screentones within arbitrarily shaped regions is very challenging due to two properties of manga: (i) pattern constancy under translation, and (ii) non-compatibility with interpolation. To circumvent this barrier, we propose learning a quantized representation of screentones that is translation-invariant and pointwisely representable through a tailored manga reconstruction network with a screentone-anchored codebook. Thanks to these merits, we can perform the re-synthesis operation using existing photo retargeting methods and achieve the desired manga retargeting results.We conducted extensive qualitative and quantitative experiments to validate the effectiveness of our method, and we achieved notably compelling results compared to alternative methods.
2D Neural Fields with Learned Discontinuities
(The Eurographics Association and John Wiley & Sons Ltd., 2025) Liu, Chenxi; Wang, Siqi; Fisher, Matthew; Aneja, Deepali; Jacobson, Alec; Bousseau, Adrien; Day, Angela
Effective representation of 2D images is fundamental in digital image processing, where traditional methods like raster and vector graphics struggle with sharpness and textural complexity, respectively. Current neural fields offer high fidelity and resolution independence but require predefined meshes with known discontinuities, restricting their utility. We observe that by treating all mesh edges as potential discontinuities, we can represent the discontinuity magnitudes as continuous variables and optimize. We further introduce a novel discontinuous neural field model that jointly approximates the target image and recovers discontinuities. Through systematic evaluations, our neural field outperforms other methods that fit unknown discontinuities with discontinuous representations, exceeding Field of Junction and Boundary Attention by over 11dB in both denoising and super-resolution tasks and achieving 3.5× smaller Chamfer distances than Mumford-Shah-based methods. It also surpasses InstantNGP with improvements of more than 5dB (denoising) and 10dB (super-resolution). Additionally, our approach shows remarkable capability in approximating complex artistic and natural images and cleaning up diffusion-generated depth maps.
FlairGPT: Repurposing LLMs for Interior Designs
(The Eurographics Association and John Wiley & Sons Ltd., 2025) Littlefair, Gabrielle; Dutt, Niladri Shekhar; Mitra, Niloy J.; Bousseau, Adrien; Day, Angela
Interior design involves the careful selection and arrangement of objects to create an aesthetically pleasing, functional, and harmonized space that aligns with the client's design brief. This task is particularly challenging, as a successful design must not only incorporate all the necessary objects in a cohesive style, but also ensure they are arranged in a way that maximizes accessibility, while adhering to a variety of affordability and usage considerations. Data-driven solutions have been proposed, but these are typically room- or domain-specific and lack explainability in their design design considerations used in producing the final layout. In this paper, we investigate if large language models (LLMs) can be directly utilized for interior design. While we find that LLMs are not yet capable of generating complete layouts, they can be effectively leveraged in a structured manner, inspired by the workflow of interior designers. By systematically probing LLMs, we can reliably generate a list of objects along with relevant constraints that guide their placement. We translate this information into a design layout graph, which is then solved using an off-the-shelf constrained optimization setup to generate the final layouts. We benchmark our algorithm in various design configurations against existing LLM-based methods and human designs, and evaluate the results using a variety of quantitative and qualitative metrics along with user studies. In summary, we demonstrate that LLMs, when used in a structured manner, can effectively generate diverse high-quality layouts, making them a viable solution for creating large-scale virtual scenes. Code is available via the project webpage.
BlendSim: Simulation on Parametric Blendshapes using Spacetime Projective Dynamics
(The Eurographics Association and John Wiley & Sons Ltd., 2025) Wu, Yuhan; Umetani, Nobuyuki; Bousseau, Adrien; Day, Angela
We propose BlendSim, a novel framework for editable simulation using spacetime optimization on the lightweight animation representation. Traditional spacetime control methods suffer from a high computational complexity, which limits their use in interactive animation. The proposed approach effectively reduces the dimensionality of the problem by representing the motion trajectories of each vertex using continuous parametric Bézier splines with variable keyframe times. Because this mesh animation representation is continuous and fully differentiable, it can be optimized such that it follows the laws of physics under various constraints. The proposed method also integrates constraints, such as collisions and cyclic motion, making it suitable for real-world applications where seamless looping and physical interactions are required. Leveraging projective dynamics, we further enhance the computational efficiency by decoupling the optimization into local parallelizable and global quadratic steps, enabling a fast and stable simulation. In addition, BlendSim is compatible with modern animation workflows and file formats, such as the glTF, making it practical way for authoring and transferring mesh animation.
SHLUT: Efficient Image Enhancement using Spatial-Aware High-Light Compensation Look-up Tables
(The Eurographics Association and John Wiley & Sons Ltd., 2025) Chen, Xin; Li, Linge; Mu, Linhong; Chen, Yan; Guan, Jingwei; Bousseau, Adrien; Day, Angela
Recently, the look-up table (LUT)-based method has achieved remarkable success in image enhancement tasks with its high efficiency and lightweight nature. However, when considering edge scenarios with limited computational resources, most existing methods fail to meet practical requirements due to their costly floating-point operations on convolution layers, which limit their general use. Moreover, most LUT-based methods may not perform well in handling high-light regions. To address these issues, we propose SHLUT, an efficient and practical image enhancement method by using spatial-aware high-light compensation look-up tables (LUTs), which comprise two parts. Firstly, we propose a spatial-aware weight predictor to reduce the computational burden. A lightweight network is trained to predict spatial-aware weight values, and then we transfer the values to the LUTs. Additionally, to correct overexposure in high-light regions, we propose a high-light compensation 3D LUT. Our proposed method allows us to directly retrieve the values from the LUTs to achieve efficient image enhancement at test time. Extensive experimental results demonstrate that SHLUT exhibits competitive performance compared to other LUT-based methods both quantitatively and qualitatively in a more efficient manner. For instance, SHLUT significantly reduces computational resources (at least 18 times in GFLOPs compared to other LUT-based methods), while excelling in high-light region handling.
Learning Image Fractals Using Chaotic Differentiable Point Splatting
(The Eurographics Association and John Wiley & Sons Ltd., 2025) Djeacoumar, Adarsh; Mujkanovic, Felix; Seidel, Hans-Peter; Leimkühler, Thomas; Bousseau, Adrien; Day, Angela
Fractal geometry, defined by self-similar patterns across scales, is crucial for understanding natural structures. This work addresses the fractal inverse problem, which involves extracting fractal codes from images to explain these patterns and synthesize them at arbitrary finer scales. We introduce a novel algorithm that optimizes Iterated Function System parameters using a custom fractal generator combined with differentiable point splatting. By integrating both stochastic and gradient-based optimization techniques, our approach effectively navigates the complex energy landscapes typical of fractal inversion, ensuring robust performance and the ability to escape local minima. We demonstrate the method's effectiveness through comparisons with various fractal inversion techniques, highlighting its ability to recover high-quality fractal codes and perform extensive zoom-ins to reveal intricate patterns from just a single image.
A Semi-Implicit SPH Method for Compressible and Incompressible Flows with Improved Convergence
(The Eurographics Association and John Wiley & Sons Ltd., 2025) He, Xiaowei; Liu, Shusen; Guo, Yuzhong; Shi, Jian; Qiao, Ying; Bousseau, Adrien; Day, Angela
In simulating fluids using position-based dynamics, the accuracy and robustness depend on numerous numerical parameters, including the time step size, iteration count, and particle size, among others. This complexity can lead to unpredictable control of simulation behaviors. In this paper, we first reformulate the problem of enforcing fluid compressibility/incompressibility into an nonlinear optimization problem, and then introduce a semi-implicit successive substitution method (SISSM) to solve the nonlinear optimization problem by adjusting particle positions in parallel. In contrast to calculating an intermediate variable, such as pressure, to enforce fluid incompressibility within the position-based dynamics (PBD) framework, the proposed semiimplicit approach eliminates the necessity of such calculations. Instead, it directly employs successive substitution of particle positions to correct density errors. This method exhibits reduced dependency to numerical parameters, such as particle size and time step variations, and improves consistency and stability in simulating fluids that range from highly compressible to nearly incompressible. We validates the effectiveness of applying a variety of different techniques in accelerating the convergence rate.
CEDRL: Simulating Diverse Crowds with Example-Driven Deep Reinforcement Learning
(The Eurographics Association and John Wiley & Sons Ltd., 2025) Panayiotou, Andreas; Aristidou, Andreas; Charalambous, Panayiotis; Bousseau, Adrien; Day, Angela
The level of realism in virtual crowds is strongly affected by the presence of diverse crowd behaviors. In real life, we can observe various scenarios, ranging from pedestrians moving on a shopping street, people talking in static groups, or wandering around in a public park. Most of the existing systems optimize for specific behaviors such as goal-seeking and collision avoidance, neglecting to consider other complex behaviors that are usually challenging to capture or define. Departing from the conventional use of Supervised Learning, which requires vast amounts of labeled data and often lacks controllability, we introduce Crowds using Example-driven Deep Reinforcement Learning (CEDRL), a framework that simultaneously leverages multiple crowd datasets to model a broad spectrum of human behaviors. This approach enables agents to adaptively learn and exhibit diverse behaviors, enhancing their ability to generalize decisions across unseen states. The model can be applied to populate novel virtual environments while providing real-time controllability over the agents' behaviors. We achieve this through the design of a reward function aligned with real-world observations and by employing curriculum learning that gradually diminishes the agents' observation space. A complexity characterization metric defines each agent's high-level crowd behavior, linking it to the agent's state and serving as an input to the policy network. Additionally, a parametric reward function, influenced by the type of crowd task, facilitates the learning of a diverse and abstract behavior ''skill'' set. We evaluate our model on both training and unseen real-world data, comparing against other simulators, showing its ability to generalize across scenarios and accurately reflect the observed complexity of behaviors. We also examine our system's controllability by adjusting the complexity weight, discovering that higher values lead to more complex behaviors such as wandering, static interactions, and group dynamics like joining or leaving. Finally, we demonstrate our model's capabilities in novel synthetic scenarios.
Rest Shape Optimization for Sag-Free Discrete Elastic Rods
(The Eurographics Association and John Wiley & Sons Ltd., 2025) Takahashi, Tetsuya; Batty, Christopher; Bousseau, Adrien; Day, Angela
We propose a new rest shape optimization framework to achieve sag-free simulations of discrete elastic rods. To optimize rest shape parameters, we formulate a minimization problem based on the kinetic energy with a regularizer while imposing box constraints on these parameters to ensure the system's stability. Our method solves the resulting constrained minimization problem via the Gauss-Newton algorithm augmented with penalty methods. We demonstrate that the optimized rest shape parameters enable discrete elastic rods to achieve static equilibrium for a wide range of strand geometries and material parameters.

Browse

Browsing EG2025 by Issue Date

Results Per Page

Sort Options