Pub Date : 2025-10-01DOI: 10.1016/j.cag.2025.104450
Hans-Jörg Schulz, Marco Angelini
{"title":"Foreword to special section: Highlights from EuroVA 2024","authors":"Hans-Jörg Schulz, Marco Angelini","doi":"10.1016/j.cag.2025.104450","DOIUrl":"10.1016/j.cag.2025.104450","url":null,"abstract":"","PeriodicalId":50628,"journal":{"name":"Computers & Graphics-Uk","volume":"133 ","pages":"Article 104450"},"PeriodicalIF":2.8,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145269535","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-09-29DOI: 10.1016/j.cag.2025.104446
Victor Flávio de Andrade Araujo , Angelo Brandelli Costa , Soraia Raupp Musse
Virtual Humans (VHs) are becoming increasingly realistic, raising questions about how users perceive their gender and emotions. In this study, we investigate how textually assigned gender and visual facial features influence both gender attribution and emotion recognition in VHs. Two experiments were conducted. In the first, participants evaluated a nonbinary VH animated with expressions performed by both male and female actors. In the second part, participants assessed binary male and female VHs animated by either real actors or data-driven facial styles. Results show that users often rely on textual gender cues and facial features to assign gender to VHs. Emotion recognition was more accurate when expressions were performed by actresses or derived from facial styles, particularly in nonbinary models. Notably, participants more consistently attributed gender according to textual cues when the VH was visually androgynous, suggesting that the absence of strong gendered facial markers increases the reliance on textual information. These findings offer insights for designing more inclusive and perceptually coherent virtual agents.
{"title":"Examining the attribution of gender and the perception of emotions in virtual humans","authors":"Victor Flávio de Andrade Araujo , Angelo Brandelli Costa , Soraia Raupp Musse","doi":"10.1016/j.cag.2025.104446","DOIUrl":"10.1016/j.cag.2025.104446","url":null,"abstract":"<div><div>Virtual Humans (VHs) are becoming increasingly realistic, raising questions about how users perceive their gender and emotions. In this study, we investigate how textually assigned gender and visual facial features influence both gender attribution and emotion recognition in VHs. Two experiments were conducted. In the first, participants evaluated a nonbinary VH animated with expressions performed by both male and female actors. In the second part, participants assessed binary male and female VHs animated by either real actors or data-driven facial styles. Results show that users often rely on textual gender cues and facial features to assign gender to VHs. Emotion recognition was more accurate when expressions were performed by actresses or derived from facial styles, particularly in nonbinary models. Notably, participants more consistently attributed gender according to textual cues when the VH was visually androgynous, suggesting that the absence of strong gendered facial markers increases the reliance on textual information. These findings offer insights for designing more inclusive and perceptually coherent virtual agents.</div></div>","PeriodicalId":50628,"journal":{"name":"Computers & Graphics-Uk","volume":"133 ","pages":"Article 104446"},"PeriodicalIF":2.8,"publicationDate":"2025-09-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145269537","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-09-27DOI: 10.1016/j.cag.2025.104447
Wenjie Liu, Ling You, Xiaoyan Yang, Dingbo Lu, Yang Li, Changbo Wang
Recently, Neural Radiance Fields (NeRF) has seen a surge in popularity, driven by its ability to generate high-fidelity novel view synthesized images. However, unexpected “floating ghost” artifacts usually emerge with limited training views and intricate optical phenomena. This issue stems from the inherent ambiguities in radiance fields, rooted in the fundamental volume rendering equation and the unrestricted learning paradigms in multi-layer perceptrons. In this paper, we introduce Convolutional Neural Radiance Fields (CeRF), a novel approach to model the derivatives of radiance along rays and solve the ambiguities through a fully neural rendering pipeline. To this end, a single-surface selection mechanism involving both a modified softmax function and an ideal point is proposed to implement our radiance derivative fields. Furthermore, a structured neural network architecture with 1D convolutional operations is employed to further boost the performance by extracting latent ray representations. Extensive experiments demonstrate the promising results of our proposed model compared with existing state-of-the-art approaches.
{"title":"CeRF: Convolutional neural radiance derivative fields for new view synthesis","authors":"Wenjie Liu, Ling You, Xiaoyan Yang, Dingbo Lu, Yang Li, Changbo Wang","doi":"10.1016/j.cag.2025.104447","DOIUrl":"10.1016/j.cag.2025.104447","url":null,"abstract":"<div><div>Recently, Neural Radiance Fields (NeRF) has seen a surge in popularity, driven by its ability to generate high-fidelity novel view synthesized images. However, unexpected “floating ghost” artifacts usually emerge with limited training views and intricate optical phenomena. This issue stems from the inherent ambiguities in radiance fields, rooted in the fundamental volume rendering equation and the unrestricted learning paradigms in multi-layer perceptrons. In this paper, we introduce Convolutional Neural Radiance Fields (CeRF), a novel approach to model the derivatives of radiance along rays and solve the ambiguities through a fully neural rendering pipeline. To this end, a single-surface selection mechanism involving both a modified softmax function and an ideal point is proposed to implement our radiance derivative fields. Furthermore, a structured neural network architecture with 1D convolutional operations is employed to further boost the performance by extracting latent ray representations. Extensive experiments demonstrate the promising results of our proposed model compared with existing state-of-the-art approaches.</div></div>","PeriodicalId":50628,"journal":{"name":"Computers & Graphics-Uk","volume":"133 ","pages":"Article 104447"},"PeriodicalIF":2.8,"publicationDate":"2025-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145222446","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-09-26DOI: 10.1016/j.cag.2025.104434
Mateus Pinto da Silva , Sabrina P.L.P. Correa , Mariana A.R. Schaefer , Julio C.S. Reis , Ian M. Nunes , Jefersson A. dos Santos , Hugo N. Oliveira
Deep Learning based on Remote Sensing has become a powerful tool to increase agricultural productivity, mitigate the effects of climate change, and monitor deforestation. However, there is a lack of standardization and appropriate taxonomic classification of the literature available in the context of informatics. Taking advantage of the categories already available in the literature, this paper provides an overview of the relevant literature categorized into five main applications: Parcel Segmentation, Crop Mapping, Crop Yielding, Land Use and Land Cover, and Change Detection. We review notable trends, including the transition from traditional to deep learning, convolutional models, recurrent and attention-based models, and generative strategies. We also map the use of Self-Supervised Learning through contrastive, non-contrastive, data masking and hybrid semi-supervised pretraining for the aforementioned applications with an experimental benchmark for Post-Harvest Crop Mapping models, and present our solution, SITS-Siam, which achieves top performance on two of the three datasets tested. In addition, we provide a comprehensive overview of publicly available datasets for these applications and also unlabeled datasets for Remote Sensing in general. We hope that our work can be useful as a guide for future work in this context. The benchmark code and the pre-trained weights are available in https://github.com/mateuspinto/rs-agriculture-survey-extended.
{"title":"Advancing agricultural remote sensing: A comprehensive review of deep supervised and Self-Supervised Learning for crop monitoring","authors":"Mateus Pinto da Silva , Sabrina P.L.P. Correa , Mariana A.R. Schaefer , Julio C.S. Reis , Ian M. Nunes , Jefersson A. dos Santos , Hugo N. Oliveira","doi":"10.1016/j.cag.2025.104434","DOIUrl":"10.1016/j.cag.2025.104434","url":null,"abstract":"<div><div>Deep Learning based on Remote Sensing has become a powerful tool to increase agricultural productivity, mitigate the effects of climate change, and monitor deforestation. However, there is a lack of standardization and appropriate taxonomic classification of the literature available in the context of informatics. Taking advantage of the categories already available in the literature, this paper provides an overview of the relevant literature categorized into five main applications: Parcel Segmentation, Crop Mapping, Crop Yielding, Land Use and Land Cover, and Change Detection. We review notable trends, including the transition from traditional to deep learning, convolutional models, recurrent and attention-based models, and generative strategies. We also map the use of Self-Supervised Learning through contrastive, non-contrastive, data masking and hybrid semi-supervised pretraining for the aforementioned applications with an experimental benchmark for Post-Harvest Crop Mapping models, and present our solution, SITS-Siam, which achieves top performance on two of the three datasets tested. In addition, we provide a comprehensive overview of publicly available datasets for these applications and also unlabeled datasets for Remote Sensing in general. We hope that our work can be useful as a guide for future work in this context. The benchmark code and the pre-trained weights are available in <span><span>https://github.com/mateuspinto/rs-agriculture-survey-extended</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":50628,"journal":{"name":"Computers & Graphics-Uk","volume":"133 ","pages":"Article 104434"},"PeriodicalIF":2.8,"publicationDate":"2025-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145269534","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-09-25DOI: 10.1016/j.cag.2025.104448
Shufang Zhang , Hang Qian , Minxue Ni , Yaxuan Li , Wenxin Ding , Jun Liu
With the rapid development of electronic commerce, virtual try-on technology has become an essential tool to satisfy consumers’ personalised clothing preferences. Diffusion-based virtual try-on systems aim to naturally align garments with target individuals, generating realistic and detailed try-on images. However, existing methods overlook the importance of garment size variations in meeting personalised consumer needs. To address this, we propose a novel virtual try-on method named SV-VTON, which introduces garment sizing concepts into virtual try-on tasks. The SV-VTON method first generates refined masks for multiple garment sizes, then integrates these masks with garment images at varying proportions, enabling virtual try-on simulations across different sizes. In addition, we develop a specialised size evaluation module to quantitatively assess the accuracy of size variations. This module calculates differences between generated size increments and international sizing standards, providing objective measurements of size accuracy. To further validate SV-VTON’s generalisation capability across different models, we conduct experiments on multiple SOTA Diffusion models. The results demonstrate that SV-VTON consistently achieves precise multi-size virtual try-on across various SOTA models, and validates the effectiveness and rationality of the proposed method, significantly fulfilling users’ personalised multi-size virtual try-on requirements.
{"title":"Diffusion model-based size variable virtual try-on technology and evaluation method","authors":"Shufang Zhang , Hang Qian , Minxue Ni , Yaxuan Li , Wenxin Ding , Jun Liu","doi":"10.1016/j.cag.2025.104448","DOIUrl":"10.1016/j.cag.2025.104448","url":null,"abstract":"<div><div>With the rapid development of electronic commerce, virtual try-on technology has become an essential tool to satisfy consumers’ personalised clothing preferences. Diffusion-based virtual try-on systems aim to naturally align garments with target individuals, generating realistic and detailed try-on images. However, existing methods overlook the importance of garment size variations in meeting personalised consumer needs. To address this, we propose a novel virtual try-on method named SV-VTON, which introduces garment sizing concepts into virtual try-on tasks. The SV-VTON method first generates refined masks for multiple garment sizes, then integrates these masks with garment images at varying proportions, enabling virtual try-on simulations across different sizes. In addition, we develop a specialised size evaluation module to quantitatively assess the accuracy of size variations. This module calculates differences between generated size increments and international sizing standards, providing objective measurements of size accuracy. To further validate SV-VTON’s generalisation capability across different models, we conduct experiments on multiple SOTA Diffusion models. The results demonstrate that SV-VTON consistently achieves precise multi-size virtual try-on across various SOTA models, and validates the effectiveness and rationality of the proposed method, significantly fulfilling users’ personalised multi-size virtual try-on requirements.</div></div>","PeriodicalId":50628,"journal":{"name":"Computers & Graphics-Uk","volume":"133 ","pages":"Article 104448"},"PeriodicalIF":2.8,"publicationDate":"2025-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145222447","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This paper aims to evaluate how different combinations of multisensory stimuli affect the vividness of users’ mental imagery in the context of virtual tourism. To this end, a between-subjects experimental study was conducted with 94 participants, who were allocated to either a positive or a negative immersive virtual environment. The positive environment contained only pleasant multisensory stimuli, whereas the negative contained only unpleasant stimuli. For each of the virtual experiences, a multisensory treasure hunt was developed, where each object found corresponded to a planned combination of stimuli (positive or negative, accordingly). The results showed that positive stimuli involving a higher number of sensory modalities resulted in higher reported vividness. In contrast, when the same multisensory modalities were delivered with negative stimuli, vividness levels decreased — an effect we attribute to potential cognitive overload. Nevertheless, some reduced negative combinations (audiovisual with smell and audiovisual with haptics) remained effective, indicating that olfactory and haptic cues play an important role in shaping users’ vividness of mental imagery, even in negative contexts.
{"title":"The vividness of mental imagery in virtual reality: A study on multisensory experiences in virtual tourism","authors":"Mariana Magalhães , Miguel Melo , António Coelho , Maximino Bessa","doi":"10.1016/j.cag.2025.104443","DOIUrl":"10.1016/j.cag.2025.104443","url":null,"abstract":"<div><div>This paper aims to evaluate how different combinations of multisensory stimuli affect the vividness of users’ mental imagery in the context of virtual tourism. To this end, a between-subjects experimental study was conducted with 94 participants, who were allocated to either a positive or a negative immersive virtual environment. The positive environment contained only pleasant multisensory stimuli, whereas the negative contained only unpleasant stimuli. For each of the virtual experiences, a multisensory treasure hunt was developed, where each object found corresponded to a planned combination of stimuli (positive or negative, accordingly). The results showed that positive stimuli involving a higher number of sensory modalities resulted in higher reported vividness. In contrast, when the same multisensory modalities were delivered with negative stimuli, vividness levels decreased — an effect we attribute to potential cognitive overload. Nevertheless, some reduced negative combinations (audiovisual with smell and audiovisual with haptics) remained effective, indicating that olfactory and haptic cues play an important role in shaping users’ vividness of mental imagery, even in negative contexts.</div></div>","PeriodicalId":50628,"journal":{"name":"Computers & Graphics-Uk","volume":"133 ","pages":"Article 104443"},"PeriodicalIF":2.8,"publicationDate":"2025-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145222445","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-09-24DOI: 10.1016/j.cag.2025.104445
Jianwu Long, Yuanqin Liu, Shaoyi Wang, Shuang Chen, Qi Luo
The objective of interactive image segmentation is to generate a segmentation mask for the target object using minimal user interaction. During the interaction process, segmentation results from previous iterations are typically used as feedback to guide subsequent user input. However, existing approaches often concatenate user interactions, feedback, and low-level image features as direct inputs to the network, overlooking the high-level semantic information contained in the feedback and the issue of information dilution from click signals. To address these limitations, we propose a novel interactive image segmentation model called Multi-stage Click Fusion with deep Feedback Aggregation(MCFA). MCFA introduces a new information fusion strategy. Specifically, for feedback information, it refines previous-round feedback using deep features and integrates the optimized feedback into the feature representation. For user clicks, MCFA performs multi-stage fusion to enhance click propagation while constraining its direction through the refined feedback. Experimental results demonstrate that MCFA consistently outperforms existing methods across five benchmark datasets: GrabCut, Berkeley, SBD, DAVIS and CVC-ClinicDB.
交互式图像分割的目的是使用最少的用户交互为目标对象生成分割掩码。在交互过程中，以前迭代的分割结果通常用作指导后续用户输入的反馈。然而，现有的方法通常将用户交互、反馈和低级图像特征连接起来作为网络的直接输入，忽略了反馈中包含的高级语义信息和点击信号的信息稀释问题。为了解决这些限制，我们提出了一种新的交互式图像分割模型，称为深度反馈聚合的多阶段点击融合（Multi-stage Click Fusion with deep Feedback Aggregation， MCFA）。MCFA引入了一种新的信息融合策略。具体而言，对于反馈信息，它使用深度特征对前一轮反馈进行细化，并将优化后的反馈集成到特征表示中。对于用户点击，MCFA进行多阶段融合，增强点击传播，同时通过精细反馈约束点击传播方向。实验结果表明，MCFA在五个基准数据集（GrabCut、Berkeley、SBD、DAVIS和CVC-ClinicDB）上始终优于现有方法。
{"title":"Fusing multi-stage clicks with deep feedback aggregation for interactive image segmentation","authors":"Jianwu Long, Yuanqin Liu, Shaoyi Wang, Shuang Chen, Qi Luo","doi":"10.1016/j.cag.2025.104445","DOIUrl":"10.1016/j.cag.2025.104445","url":null,"abstract":"<div><div>The objective of interactive image segmentation is to generate a segmentation mask for the target object using minimal user interaction. During the interaction process, segmentation results from previous iterations are typically used as feedback to guide subsequent user input. However, existing approaches often concatenate user interactions, feedback, and low-level image features as direct inputs to the network, overlooking the high-level semantic information contained in the feedback and the issue of information dilution from click signals. To address these limitations, we propose a novel interactive image segmentation model called Multi-stage Click Fusion with deep Feedback Aggregation(MCFA). MCFA introduces a new information fusion strategy. Specifically, for feedback information, it refines previous-round feedback using deep features and integrates the optimized feedback into the feature representation. For user clicks, MCFA performs multi-stage fusion to enhance click propagation while constraining its direction through the refined feedback. Experimental results demonstrate that MCFA consistently outperforms existing methods across five benchmark datasets: GrabCut, Berkeley, SBD, DAVIS and CVC-ClinicDB.</div></div>","PeriodicalId":50628,"journal":{"name":"Computers & Graphics-Uk","volume":"133 ","pages":"Article 104445"},"PeriodicalIF":2.8,"publicationDate":"2025-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145160121","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Sparse-view 3D reconstruction has garnered widespread attention due to its demand for high-quality reconstruction under low-sampling data conditions. Existing NeRF-based methods rely on dense views and substantial computational resources, while 3DGS is limited by multi-view inconsistency and insufficient geometric detail recovery, making it challenging to achieve ideal results in sparse-view scenarios. This paper introduces HR-2DGS, a novel hybrid regularization framework based on 2D Gaussian Splatting (2DGS), which significantly enhances multi-view consistency and geometric recovery by dynamically fusing monocular depth estimates with rendered depth maps, incorporating hybrid normal regularization techniques. To further refine local details, we introduce a per-pixel depth normalization that leverages each pixel’s neighborhood statistics to emphasize fine-scale geometric variations. Experimental results on the LLFF and DTU datasets demonstrate that HR-2DGS outperforms existing methods in terms of PSNR, SSIM, and LPIPS, while requiring only 2.5GB of memory and a few minutes of training time for efficient training and real-time rendering.
{"title":"HR-2DGS: Hybrid regularization for sparse-view 3D reconstruction with 2D Gaussian splatting","authors":"Yong Tang, Jiawen Yan, Yu Li, Yu Liang, Feng Wang, Jing Zhao","doi":"10.1016/j.cag.2025.104444","DOIUrl":"10.1016/j.cag.2025.104444","url":null,"abstract":"<div><div>Sparse-view 3D reconstruction has garnered widespread attention due to its demand for high-quality reconstruction under low-sampling data conditions. Existing NeRF-based methods rely on dense views and substantial computational resources, while 3DGS is limited by multi-view inconsistency and insufficient geometric detail recovery, making it challenging to achieve ideal results in sparse-view scenarios. This paper introduces HR-2DGS, a novel hybrid regularization framework based on 2D Gaussian Splatting (2DGS), which significantly enhances multi-view consistency and geometric recovery by dynamically fusing monocular depth estimates with rendered depth maps, incorporating hybrid normal regularization techniques. To further refine local details, we introduce a per-pixel depth normalization that leverages each pixel’s neighborhood statistics to emphasize fine-scale geometric variations. Experimental results on the LLFF and DTU datasets demonstrate that HR-2DGS outperforms existing methods in terms of PSNR, SSIM, and LPIPS, while requiring only 2.5GB of memory and a few minutes of training time for efficient training and real-time rendering.</div></div>","PeriodicalId":50628,"journal":{"name":"Computers & Graphics-Uk","volume":"133 ","pages":"Article 104444"},"PeriodicalIF":2.8,"publicationDate":"2025-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145160123","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-09-23DOI: 10.1016/j.cag.2025.104392
Niklas Merk, Anna Sterzik, Kai Lawonn
The solvent-excluded surface (SES) is essential for revealing molecular shape and solvent accessibility in applications such as molecular modeling, drug discovery, and protein folding. Its signed distance field (SDF) delivers a continuous, differentiable surface representation that enables efficient rendering, analysis, and interaction in volumetric visualization frameworks. However, analytic methods that compute the SDF of the SES cannot run at interactive rates on large biomolecular complexes, and grid-based methods tend to result in significant approximation errors, depending on molecular size and grid resolution. We address these limitations with DeepSES, a neural inference pipeline that predicts the SES SDF directly from the computationally simpler van der Waals (vdW) SDF on a fixed high-resolution grid. By employing an adaptive volume-filtering scheme that directs processing only to visible regions near the molecular surface, DeepSES yields interactive frame rates irrespective of molecule size. By offering multiple network configurations, DeepSES enables practitioners to balance inference time against prediction accuracy. In benchmarks on molecules ranging from one thousand to nearly four million atoms, our fastest configuration achieves real-time frame rates with a sub-angstrom mean error, while our highest-accuracy variant sustains interactive performance and outperforms state-of-the-art methods in terms of surface quality. By replacing costly algorithmic solvers with selective neural prediction, DeepSES provides a scalable, high-resolution solution for interactive biomolecular visualization.
{"title":"DeepSES: Learning solvent-excluded surfaces via neural signed distance fields","authors":"Niklas Merk, Anna Sterzik, Kai Lawonn","doi":"10.1016/j.cag.2025.104392","DOIUrl":"10.1016/j.cag.2025.104392","url":null,"abstract":"<div><div>The solvent-excluded surface (SES) is essential for revealing molecular shape and solvent accessibility in applications such as molecular modeling, drug discovery, and protein folding. Its signed distance field (SDF) delivers a continuous, differentiable surface representation that enables efficient rendering, analysis, and interaction in volumetric visualization frameworks. However, analytic methods that compute the SDF of the SES cannot run at interactive rates on large biomolecular complexes, and grid-based methods tend to result in significant approximation errors, depending on molecular size and grid resolution. We address these limitations with DeepSES, a neural inference pipeline that predicts the SES SDF directly from the computationally simpler van der Waals (vdW) SDF on a fixed high-resolution grid. By employing an adaptive volume-filtering scheme that directs processing only to visible regions near the molecular surface, DeepSES yields interactive frame rates irrespective of molecule size. By offering multiple network configurations, DeepSES enables practitioners to balance inference time against prediction accuracy. In benchmarks on molecules ranging from one thousand to nearly four million atoms, our fastest configuration achieves real-time frame rates with a sub-angstrom mean error, while our highest-accuracy variant sustains interactive performance and outperforms state-of-the-art methods in terms of surface quality. By replacing costly algorithmic solvers with selective neural prediction, DeepSES provides a scalable, high-resolution solution for interactive biomolecular visualization.</div></div>","PeriodicalId":50628,"journal":{"name":"Computers & Graphics-Uk","volume":"133 ","pages":"Article 104392"},"PeriodicalIF":2.8,"publicationDate":"2025-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145160124","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Quad-dominant meshes are popular with animation designers and can efficiently be generated from point clouds. To join primary regions, quad-dominant meshes include non-4-valent vertices and non-quad regions. To transition between regions of rich detail and simple shape, quad-dominant meshes commonly use a cascade of triangles that reduce the number of parallel quad strips from to 2. For these cascades, the Narrowing-Cascade spline, short NC, provides a new shape-optimized spline surface. NC can treat cascade meshes as B-spline-like control nets. For , as opposed to , cascades have interior points that both guide and complicate the construction of the output tensor-product NCspline. The NC spline follows the input mesh, including interior points, and delivers a high-quality curved surface of low degree.
{"title":"Narrowing-Cascade splines for control nets that shed mesh lines","authors":"Serhat Cam , Erkan Gunpinar , Kȩstutis Karčiauskas , Jörg Peters","doi":"10.1016/j.cag.2025.104441","DOIUrl":"10.1016/j.cag.2025.104441","url":null,"abstract":"<div><div>Quad-dominant meshes are popular with animation designers and can efficiently be generated from point clouds. To join primary regions, quad-dominant meshes include non-4-valent vertices and non-quad regions. To transition between regions of rich detail and simple shape, quad-dominant meshes commonly use a cascade of <span><math><mrow><mi>n</mi><mo>−</mo><mn>1</mn></mrow></math></span> triangles that reduce the number of parallel quad strips from <span><math><mrow><mi>n</mi><mo>+</mo><mn>1</mn></mrow></math></span> to 2. For these cascades, the Narrowing-Cascade spline, short NC<span><math><msup><mrow></mrow><mrow><mi>n</mi></mrow></msup></math></span>, provides a new shape-optimized <span><math><msup><mrow><mi>G</mi></mrow><mrow><mn>1</mn></mrow></msup></math></span> spline surface. NC<span><math><msup><mrow></mrow><mrow><mi>n</mi></mrow></msup></math></span> can treat cascade meshes as B-spline-like control nets. For <span><math><mrow><mi>n</mi><mo>></mo><mn>3</mn></mrow></math></span>, as opposed to <span><math><mrow><mi>n</mi><mo>=</mo><mn>2</mn><mo>,</mo><mn>3</mn></mrow></math></span>, cascades have interior points that both guide and complicate the construction of the output tensor-product NC<span><math><msup><mrow></mrow><mrow><mspace></mspace></mrow></msup></math></span>spline. The NC<span><math><msup><mrow></mrow><mrow><mi>n</mi></mrow></msup></math></span> spline follows the input mesh, including interior points, and delivers a high-quality curved surface of low degree.</div></div>","PeriodicalId":50628,"journal":{"name":"Computers & Graphics-Uk","volume":"133 ","pages":"Article 104441"},"PeriodicalIF":2.8,"publicationDate":"2025-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145269530","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号