44-Issue 6

Permanent URI for this collection

https://diglib.eg.org/handle/10.2312/3607243

Browse

Now showing 1 - 20 of 25

Real-Time and Controllable Reactive Motion Synthesis via Intention Guidance
(The Eurographics Association and John Wiley & Sons Ltd., 2025) Zhang, Xiaotang; Chang, Ziyi; Men, Qianhui; Shum, Hubert P. H.; Wimmer, Michael; Alliez, Pierre; Westermann, Rüdiger
We propose a real-time method for reactive motion synthesis based on the known trajectory of an input character, predicting instant reactions using only historical, user-controlled motions. Our method handles the uncertainty of future movements by introducing an intention predictor, which forecasts key joint intentions to make pose prediction more deterministic from the historical interaction. The intention is later encoded into the latent space of its reactive motion, matched with a codebook that represents mappings between input and output. It samples from the categorical distribution for pose generation and strengthens model robustness through adversarial training. Unlike previous offline approaches, the system can recursively generate intentions and reactive motions using feedback from earlier steps, enabling real-time, long-term realistic interactive synthesis. Both quantitative and qualitative experiments show our approach outperforms other matching-based motion synthesis approaches, delivering superior stability and generalisability. In our method, the user can also actively influence the outcome by controlling the moving directions, creating a personalised interaction path that deviates from predefined trajectories.
GeoDEN: A Visual Exploration Tool for Analyzing the Geographic Spread of Dengue Serotypes
(The Eurographics Association and John Wiley & Sons Ltd., 2025) Marler, Aidan; Roell, Yannik; Knoblauch, Steffen; Messina Jane, P.; Jaenisch, Thomas; Karimzadeh, Mohammad; Wimmer, Michael; Alliez, Pierre; Westermann, Rüdiger
Static maps and animations remain popular in spatial epidemiology of dengue, limiting the analytical depth and scope of visualizations. Over half of the global population live in dengue endemic regions. Understanding the spatiotemporal dynamics of the four closely related dengue serotypes, and their immunological interactions, remains a challenge at a global scale. To facilitate this understanding, we worked with dengue epidemiologists in a user-centred design framework to create GeoDEN, an exploratory visualization tool that empowers experts to investigate spatiotemporal patterns in dengue serotype reports. The tool has several linked visualizations and filtering mechanisms, enabling analysis at a range of spatial and temporal scales. To identify successes and failures, we present both insight-based and value-driven evaluations. Our domain experts found GeoDEN valuable, verifying existing hypotheses and uncovering novel insights that warrant further investigation by the epidemiology community. The developed visual exploration approach can be adapted for exploring other epidemiology and disease incident datasets.
Optimal Dimensionality Selection Using Hull Heatmaps for Single-Cell Analysis
(The Eurographics Association and John Wiley & Sons Ltd., 2025) Jeong, Haejin; Jeong, Hyoung-oh; Lee, Semin; Jeong, Won-Ki; Wimmer, Michael; Alliez, Pierre; Westermann, Rüdiger
Single-cell RNA sequencing (scRNA-seq) has gained prominence as a valuable technique for examining cellular gene expression patterns at the individual cell level. In the analysis of scRNA-seq datasets, it is common practice to visualise a subset of principal components (PCs), obtained via principal component analysis (PCA), using dimensionality reduction techniques such as t-stochastic neighbour embedding (t-SNE). Determining the number of PCs (i.e. dimensionality) is a critical step that influences the outcome of single-cell analysis, and this process typically requires a labour-intensive manual assessment involving the inspection of numerous projection plots. To address this challenge, we present a visualisation system that assists analysts in efficiently determining the optimal dimensionality of scRNA-seq data. The proposed system employs two hull heatmaps, a cell type heatmap and a cluster heatmap, which offer comprehensive representations of target cells of multiple cell types across various dimensionalities through the utilisation of a convex hull-embedded colour map. The cell type heatmap shows overlaps between cell types, and the cluster heatmap compares cell clustering results. The proposed hull heatmaps effectively alleviate the labourious task of manually evaluating hundreds of projection plots for searching for the optimal dimensionality. Additionally, our system offers interactive visualisation of gene expression levels and an intuitive lasso selection tool, thereby enabling analysts to progressively refine the convex hulls on the hull heatmaps. We validated the usefulness of the proposed system through two quantitative evaluations and three case studies.
Self-Supervised Image Harmonization via Region-Aware Harmony Classification
(The Eurographics Association and John Wiley & Sons Ltd., 2025) Tian, Chenyang; Wang, Xinbo; Zhang, Qing; Wimmer, Michael; Alliez, Pierre; Westermann, Rüdiger
Image harmonization is a widely used technique in image composition, which aims to adjust the appearance of the composited foreground object according to the style of the background image so that the resulting composited image is visually natural and appears to be photographed. Previous methods are mostly trained in a fully supervised manner, while demonstrating promising results, they do not generalize well to complex unseen cases involving significant style and semantic difference between the composited foreground object and the background image. In this paper, we present a self-supervised image harmonization framework that enables superior performance on complex cases. To do so, we first synthesize a large amount of data with wide diversity for training. We then develop an attentive harmonization module to adaptively adjust the foreground appearance by querying relevant background features. To allow more effective image harmonization, we develop a region-aware harmony classifier to explicitly judge whether an image is harmonious or not. Experiments on several datasets show that our method performs favourably against previous methods. Our code will be made publicly available.
Comparative Study of Four Visualization Techniques and Positional Variations for Displaying Exercise Data on Smartwatches
(The Eurographics Association and John Wiley & Sons Ltd., 2025) Liu, Yu; Xia, Zhouxuan; Du, Jinyuan; Wimmer, Michael; Alliez, Pierre; Westermann, Rüdiger
As smartwatches become increasingly prevalent, their built-in sensors provide a rich source for gathering various personal data, including physical activity and health metrics. We found that different brands and models use various visualization techniques. However, the effectiveness of these visualizations within the limited display space of smartwatches remains unclear. Therefore, this paper compares four popular visualizations—bar charts, radial bar charts, donut charts and multi-donut charts—used for displaying activity data on smartwatches. The evaluation focuses on their performance in three common user tasks: counting completed goals, estimating completion percentage and estimating exercise duration. Additionally, the study investigates the impact of the positioning of the target data item within these visualizations on user performance. Our results indicate that bar charts are superior in terms of task completion time across all tasks. Radial bar charts and multi-donut charts are most effective in helping users perceive the completion ratio (percentage) of each activity and understand the time taken for each activity metric (in minutes). Interestingly, we found that the positioning of data items within the visualizations significantly influences user performance in many cases. Furthermore, it was noted that the visualizations users favoured the most were generally those that enabled them to achieve the highest accuracy in task completion. These insights provide valuable guidelines for future designs in visualizing exercise data on smartwatches. Supplementary material is available at https://osf.io/5u2ph/.
Exploratory Analysis of Scientific Publications for University Governance
(The Eurographics Association and John Wiley & Sons Ltd., 2025) Gràcia, A.; Padró, L.; Alarcon, E.; Vázquez, P.; Wimmer, Michael; Alliez, Pierre; Westermann, Rüdiger
Research-oriented universities often comprise numerous researchers of various types and possess complex research structures that encompass research groups, departments, laboratories, and research institutes. In this situation, understanding the university's strengths and areas of excellence requires careful examination. Additionally, individuals at different levels of governance (e.g., department heads, directors of research institutes, rectors) may seek to establish synergies among researchers to tackle issues such as international project applications or industry technology transfer. University officials and faculty members frequently require the expertise of specific research groups or individuals, but struggle to obtain this information beyond their personal networks. This limits their ability to locate necessary resources effectively. Fortunately, most institutions have databases containing publications that could provide valuable insights into areas of strength within the university. In this article, we present a visual analysis application capable of addressing these questions and assisting management in making informed decisions regarding governance measures such as creating new research institutes. Our system has been evaluated by domain experts, who found it highly beneficial and expressed interest in utilising it regularly.
Adaptive and Iterative Point Cloud Denoising with Score-Based Diffusion Model
(The Eurographics Association and John Wiley & Sons Ltd., 2025) Wang, Zhaonan; Li, Manyi; Xin, Shiqing; Tu, Changhe; Wimmer, Michael; Alliez, Pierre; Westermann, Rüdiger
Point cloud denoising task aims to recover the clean point cloud from the scanned data coupled with different levels or patterns of noise. The recent state-of-the-art methods often train deep neural networks to update the point locations towards the clean point cloud, and empirically repeat the denoising process several times in order to obtain the denoised results. It is not clear how to efficiently arrange the iterative denoising processes to deal with different levels or patterns of noise. In this paper, we propose an adaptive and iterative point cloud denoising method based on the score-based diffusion model. For a given noisy point cloud, we first estimate the noise variation and determine an adaptive denoising schedule with appropriate step sizes, then invoke the trained network iteratively to update point clouds following the adaptive schedule. To facilitate this adaptive and iterative denoising process, we design the network architecture and a two-stage sampling strategy for the network training to enable feature fusion and gradient fusion for iterative denoising. Compared to the state-of-the-art point cloud denoising methods, our approach obtains clean and smooth denoised point clouds, while preserving the shape boundary and details better. Our results not only outperform the other methods both qualitatively and quantitatively, but also are preferable on the synthetic dataset with different patterns of noises, as well as the real-scanned dataset.
Gaze-Aware Visualisation: Design Considerations and Research Agenda
(The Eurographics Association and John Wiley & Sons Ltd., 2025) Jianu, Radu; Silva, Nelson; Rodrigues, Nils; Blascheck, Tanja; Schreck, Tobias; Weiskopf, Daniel; Wimmer, Michael; Alliez, Pierre; Westermann, Rüdiger
Eye tracking provides a unique perspective on the inherently visual discourse between visualisation systems and their users, and has recently become sufficiently precise and affordable to be integrated as regular input into workstations and virtual or augmented reality headsets alike. As such, real-time eye tracking can now contribute significantly towards the development of gaze-aware visualisations that infer and monitor users' needs to actively support their activities. To facilitate such systems we make three contributions. First, we structure and discuss design considerations for gaze-aware visualisations along four axes: measurable data; inferable data; opportunities for support; and limiting factors to beware. Second, we distill visualisation research challenges that preclude such systems. Finally, we show via three usage scenarios how to apply these design considerations to imagine how existing systems can benefit from real-time eye tracking. We combined a structured literature analysis, a consideration of suitable places for eye-tracking integration in the typical visualisation ecosystem, and design space modelling. Eye tracking has significant potential to improve the interactive visual analysis of data across many visualisation domains. Our paper attempts to provide a comprehensive, general survey and conceptual discussion in this promising field, outlining the state-of-the-art and future research opportunities.
MPACT: Mesoscopic Profiling and Abstraction of Crowd Trajectories
(The Eurographics Association and John Wiley & Sons Ltd., 2025) Lemonari, Marilena; Panayiotou, Andreas; Kyriakou, Theodoros; Pelechano, Nuria; Chrysanthou, Yiorgos; Aristidou, Andreas; Charalambous, Panayiotis; Wimmer, Michael; Alliez, Pierre; Westermann, Rüdiger
Simulating believable crowds for applications like movies or games is challenging due to the many components that comprise a realistic outcome. Users typically need to manually tune a large number of simulation parameters until they reach the desired results. We introduce MPACT, a framework that leverages image-based encoding to convert unlabelled crowd data into meaningful and controllable parameters for crowd generation. In essence, we train a parameter prediction network on a diverse set of synthetic data, which includes pairs of images and corresponding crowd profiles. The learned parameter space enables: (a) implicit crowd authoring and control, allowing users to define desired crowd scenarios using real-world trajectory data, and (b) crowd analysis, facilitating the identification of crowd behaviours in the input and the classification of unseen scenarios through operations within the latent space. We quantitatively and qualitatively evaluate our framework, comparing it against real-world data and selected baselines, while also conducting user studies with expert and novice users. Our experiments show that the generated crowds score high in terms of simulation believability, plausibility and crowd behaviour faithfulness.
3DGM: Deformable and Texturable 3D Gaussian Model via Level-of-Detail Proxy
(The Eurographics Association and John Wiley & Sons Ltd., 2025) Wang, Xiangzhi Eric; Sin, Zackary P. T.; Wimmer, Michael; Alliez, Pierre; Westermann, Rüdiger
3D Gaussian Splatting has markedly impacted neural rendering by achieving impressive fidelity and performance. Despite this achievement, it is not readily applicable to developing interactive applications. Real-time applications like XR apps and games require functions such as animation, UV mapping and level of detail (LOD) simultaneously manipulated through a 3D model. To address this need, we propose a modelling strategy analogous to typical 3D models, which we call 3D Gaussian Model (3DGM). 3DGM relies on attaching 3D Gaussians on the triangles of a mesh proxy, and the key idea is to bind sheared 3D Gaussians in texture space and re-projecting them back to world space through implicit shell mapping; this design naturally enables deformation and UV mapping via the proxy. Further, to optimize speed and fidelity based on different viewing distances, each triangle can be tessellated to change the number of involved 3D Gaussians adaptively. Application-wise, we will show that our proxy-based 3DGM is capable of enabling novel deformation without animated training data, texture transferring via UV mapping of the 3D Gaussians, and LOD rendering. The results indicate that our model achieves better fidelity for deformation and better optimization of fidelity and performance given different viewing distances. Further, we believe the results indicate the potential of our work for enabling interactive applications for 3D Gaussian Splatting.
Issue Information
(The Eurographics Association and John Wiley & Sons Ltd., 2025) Wimmer, Michael; Alliez, Pierre; Westermann, Rüdiger
Information page for issue 44(6) of Computer Graphics Forum, published in September 2025.
LEAD: Latent Realignment for Human Motion Diffusion
(The Eurographics Association and John Wiley & Sons Ltd., 2025) Andreou, Nefeli; Wang, Xi; Fernández Abrevaya, Victoria; Cani, Marie-Paule; Chrysanthou, Yiorgos; Kalogeiton, Vicky; Wimmer, Michael; Alliez, Pierre; Westermann, Rüdiger
Our goal is to generate realistic human motion from natural language. Modern methods often face a trade-off between model expressiveness and text-to-motion (T2M) alignment. Some align text and motion latent spaces but sacrifice expressiveness; others rely on diffusion models producing impressive motions but lacking semantic meaning in their latent space. This may compromise realism, diversity and applicability. Here, we address this by combining latent diffusion with a realignment mechanism, producing a novel, semantically structured space that encodes the semantics of language. Leveraging this capability, we introduce the task of textual motion inversion to capture novel motion concepts from a few examples. For motion synthesis, we evaluate LEAD on HumanML3D and KIT-ML and show comparable performance to the state-of-the-art in terms of realism, diversity and textmotion consistency. Our qualitative analysis and user study reveal that our synthesised motions are sharper, more human-like and comply better with the text compared to modern methods. For motion textual inversion (MTI), our method demonstrates improvements in capturing out-of-distribution characteristics in comparison to traditional VAEs.
Dynamic Cutting Simulation Using Elastic Snapping for Mesh Quality Optimization
(The Eurographics Association and John Wiley & Sons Ltd., 2025) Zeng, Z.; Courtecuisse, H.; Wimmer, Michael; Alliez, Pierre; Westermann, Rüdiger
In this manuscript, we present a novel cutting method that involves using a vertex-snapping strategy to fit the boundary surface onto the cutting path while avoiding generating new elements. We employ a point cloud with polynomial fitting to generate the cutting path, allowing for operation with unscheduled cuts and potential perturbations. Efficient geometry operations are developed to handle topological changes during progressive cutting. While it is challenging to optimize the mesh quality and accurately align the cut surface with the cutting path, we propose an innovative strategy that converts this geometric problem into a quasi-static elastic problem. This involves solving a constrained elastic problem within an auxiliary simulation, where the system optimizes the mesh quality when reaching equilibrium. Furthermore, we propose modifications to a GPU-based matrix-free solver, enabling efficient updates of the precomputed data stored in the GPU memory and thus ensuring real-time performance.
EyeExpand: A Low-Burden and Accurate 3D Object Selection Method With Gaze and Raycasting
(The Eurographics Association and John Wiley & Sons Ltd., 2025) Xu, X.; He, Y.; Ge, Y.; Zheng, Z.; Wimmer, Michael; Alliez, Pierre; Westermann, Rüdiger
Raycasting is a widely used object selection technique in virtual reality. However, in dense scenes, it becomes difficult for users to accurately select targets when objects are partially or fully occluded. While recent studies have introduced progressive refinement techniques based on raycasting to address these limitations, they still suffer from challenges such as high interaction complexity and difficulties in preserving the relative spatial relationships between objects within the scene. In this paper, we present a simple and efficient 3D progressive refinement technique for object selection in dense scenes while maintaining the relative spatial positions of selected objects. We compare our technique with other progressive refinement techniques and evaluate their performance and user experience in a target selection task within dense VR environments. The results show that in low- and medium-density scenarios, our technique outperforms existing progressive refinement techniques in terms of selection time. In high-density scenarios, the proposed technique significantly reduces physical effort while maintaining comparable selection times, thereby offering an improved overall interactive experience.
NCD: Normal-Guided Chamfer Distance Loss for Watertight Mesh Reconstruction from Unoriented Point Clouds
(The Eurographics Association and John Wiley & Sons Ltd., 2025) Li, Jiaxin; Tan, Jiawei; Ou, Zhilong; Wang, Hongxing; Wimmer, Michael; Alliez, Pierre; Westermann, Rüdiger
As a widely used loss function in learnable watertight mesh reconstruction from unoriented point clouds, Chamfer Distance (CD) efficiently quantifies the alignment between the sampled point cloud from the reconstructed mesh and its corresponding input point cloud. Occasionally, to enhance reconstruction fidelity, CD incorporates a normal consistency term, albeit at the cost of efficiency. In this context, normal estimation for unoriented point clouds requires computationally intensive matrix decomposition or specialized pre-trained models, whereas deriving normals for mesh-sampled points can be readily achieved using the cross product of mesh vertices. However, the reconstruction models employing CD and its variants typically rely solely on the spatial coordinates of the points, which omits normal information in favor of efficiency and deployability. To tackle this challenge, we propose a novel loss function for watertight mesh reconstruction from unoriented point clouds, termed Normal-guided Chamfer Distance (NCD). Building upon CD, NCD introduces a normal-steered weighting mechanism based on the angle between the normal at each mesh-sampled point and the vector to its corresponding input point, offering several advantages: (i) it leverages readily available mesh-sampled point normals to weight coordinate-based Euclidean distances, thus extending the capability of CD; (ii) it eliminates the need for normal estimation from input unoriented point clouds; (iii) it incurs a negligible increase in computational complexity compared to CD. We employ NCD as the training loss for point-to-mesh reconstruction with multiple models and initial watertight meshes on benchmark datasets, demonstrating its superiority over state-of-the-art CD variants.
Real-Time Neural Denoising for Volume Rendering Using Dual-Input Feature Fusion Network
(The Eurographics Association and John Wiley & Sons Ltd., 2025) Xu, Chunxiao; Xu, Xinran; Zhang, Jiatian; Liu, Yufei; Cao, Yiheng; Zhao, Lingxiao; Wimmer, Michael; Alliez, Pierre; Westermann, Rüdiger
Direct volume rendering (DVR) is a widely used technique in the visualization of volumetric data. As an important DVR technique, volumetric path tracing (VPT) simulates light transport to produce realistic rendering results, which provides enhanced perception and understanding for users, especially in the field of medical imaging. VPT, based on the Monte Carlo (MC) method, typically requires a large number of samples to generate noise-free results. However, in real-time applications, only a limited number of samples per pixel is allowed and significant noise can be created. This paper introduces a novel neural denoising approach that utilizes a new feature fusion method for VPT. Our method uses a feature decomposition technique that separates radiance into components according to noise levels. Our new decomposition technique mitigates biases found in contemporary decoupling denoising algorithms and shows better utilization of samples. A lightweight dual-input network is designed to correlate these components with noise-free ground truth. Additionally, for denoising sequences of video frames, we develop a learning-based temporal method that calculates temporal weight maps, blending reprojected results of previous frames with spatially denoised current frames. Comparative results demonstrate that our network performs faster inference than existing methods and can produce denoised output of higher quality in real time.
Augury and Forerunner: Real-Time Feedback Via Predictive Numerical Optimization and Input Prediction
(The Eurographics Association and John Wiley & Sons Ltd., 2025) Graus, J.; Gingold, Y.; Wimmer, Michael; Alliez, Pierre; Westermann, Rüdiger
In many interactive systems, user input initializes and launches an iterative optimization procedure. The goal is to provide assistive feedback to some creation/editing process. Examples include constraint-based GUI layout and complex snapping scenarios. Many geometric problems, such as fitting a shape to data, involve optimizations which may take seconds to complete (or even longer), yet require human guidance. In order to make these optimization routines practical in interactive sessions, simplifications or sacrifices must be made. Canonically, non-convex optimization problems are solved iteratively by taking a series of steps towards a solution. By their nature, there are many locally optimal solutions; which solution is found is highly dependent on an initial guess. There is a fundamental conflict between optimization and interactivity. Interrupting and restarting the optimization every time the user, e.g. moves the mouse prevents any solution from being computed until the user ceases interaction. Continuing to run the optimization procedure computes a perpetually outdated solution. This presents a particular unsolved challenge with respect to direct manipulation. Every time the user, e.g. moves the mouse, the entire optimization must be re-started with the new user input, since returning a stale result associated with the previous user state is undesirable. We propose predictive short-circuiting to reduce this fundamental tension. Our approach memoizes paths in the optimization's configuration space and predicts the trajectory of future optimization in real time, leveraging common C1 continuity assumptions. This enables direct manipulation of formerly sluggish interactions. We demonstrate our approach on geometric fitting tasks. Additionally, we evaluate complementary mouse motion prediction algorithms as a means to discard or skip optimization problems that are irrelevant to the user's intended initial configuration for a targeted optimization procedure. Predicting where the mouse cursor will be located at the end of an operation, such as dragging a model of an engine component into scanned point cloud data to perform geometric alignment, allows us to pre-emptively begin solving the targeted problem before the user finishes their movement. We take advantage of the fact that the prediction indicates the approximate energy basin the optimization procedure will need to explore.
Correction to 'Antarstick: Extracting Snow Height From Time-Lapse Photography'
(The Eurographics Association and John Wiley & Sons Ltd., 2025) Lang, M.; Mráz, R.; Trtík, M.; Stoppel, S.; Byška, J.; Kozlíková, B.; Wimmer, Michael; Alliez, Pierre; Westermann, Rüdiger
Correction note to the article "Antarstick: Extracting Snow Height From Time-Lapse Photography".
Hi3DFace: High-Realistic 3D Face Reconstruction From a Single Occluded Image
(The Eurographics Association and John Wiley & Sons Ltd., 2025) Huang, Dongjin; Shi, Yongsheng; Qu, Jiantao; Liu, Jinhua; Tang, Wen; Wimmer, Michael; Alliez, Pierre; Westermann, Rüdiger
We propose Hi3DFace, a novel framework for simultaneous de-occlusion and high-fidelity 3D face reconstruction. To address real-world occlusions, we construct a diverse facial dataset by simulating common obstructions and present TMANet, a transformer-based multi-scale attention network that effectively removes occlusions and restores clean face images. For the 3D face reconstruction stage, we propose a coarse-medium-fine self-supervised scheme. In the coarse reconstruction pipeline, we adopt a face regression network to predict 3DMM coefficients for generating a smooth 3D face. In the medium-scale reconstruction pipeline, we propose a novel depth displacement network, DDFTNet, to remove noise and restore rich details to the smooth 3D geometry. In the fine-scale reconstruction pipeline, we design a GCN (graph convolutional network) refiner to enhance the fidelity of 3D textures. Additionally, a light-aware network (LightNet) is proposed to distil lighting parameters, ensuring illumination consistency between reconstructed 3D faces and input images. Extensive experimental results demonstrate that the proposed Hi3DFace significantly outperforms state-of-the-art reconstruction methods on four public datasets, and five constructed occlusion-type datasets. Hi3DFace achieves robustness and effectiveness in removing occlusions and reconstructing 3D faces from real-world occluded facial images.
AI-ChartParser: A Method For Extracting Experimental Data From Curve Charts in Academic Papers
(The Eurographics Association and John Wiley & Sons Ltd., 2025) Yang, Wenjin; He, Jie; Zhang, Xiaotong; Gong, Haiyan; Wimmer, Michael; Alliez, Pierre; Westermann, Rüdiger
In the fields of engineering and natural sciences, curve charts serve as indispensable visualization tools for scientific research, product development and engineering design, as they encapsulate crucial data necessary for comprehensive analysis. Existing methodologies for data extraction from line charts predominantly depend on single-task models, which frequently exhibit limitations in efficiency and generalization. To overcome these challenges, we propose AI-ChartParser, an end-to-end deep learning model that employs multi-task learning to concurrently execute chart element detection, pivot point detection and curve detection. This approach effectively and efficiently parses diverse chart formats within a cohesive framework. Furthermore, we introduce an Interval-Mean Space-Numerical Mapping algorithm designed to address challenges in data range extraction, thereby significantly minimizing conversion errors. We have incorporated all the methodologies discussed in this paper to develop a comprehensive data extraction tool, facilitating the automatic conversion of line charts into tabular data. Our model exhibits exceptional performance on complex real-world datasets, achieving state-of-the-art accuracy and speed across all three tasks. To facilitate further research, the source codes and pre-trained models are released at https://github.com/ywking/ChartParser.git.

Browse

Browsing 44-Issue 6 by Issue Date

Results Per Page

Sort Options