Revolved 3D objects are widely used in industrial, manufacturing, and artistic fields, with subtractive manufacturing being a common production method. A key preprocessing step is to maximize raw material utilization by generating as many rough-machined inputs as possible from a single stock piece, which poses a packing problem constrained by tool accessibility. The main challenge is integrating tool accessibility into packing. This paper introduces the carvable packing problem for revolved objects, a critical but under-researched area in subtractive manufacturing. We propose a new carvable coarsening hull and a packing strategy that uses beam search and a bottom-up placement method to position these hulls in the stock material. Our method was tested on diverse sets of revolved objects with different geometries, and physical tests were conducted on a 5-axis machining platform, proving its ability to enhance material use and manufacturability.
{"title":"Carvable packing of revolved 3D objects for subtractive manufacturing","authors":"Chengdong Wei, Shuai Feng, Hao Xu, Qidong Zhang, Songyang Zhang, Zongzhen Li, Changhe Tu, Haisen Zhao","doi":"10.1016/j.gmod.2025.101282","DOIUrl":"10.1016/j.gmod.2025.101282","url":null,"abstract":"<div><div>Revolved 3D objects are widely used in industrial, manufacturing, and artistic fields, with subtractive manufacturing being a common production method. A key preprocessing step is to maximize raw material utilization by generating as many rough-machined inputs as possible from a single stock piece, which poses a packing problem constrained by tool accessibility. The main challenge is integrating tool accessibility into packing. This paper introduces the carvable packing problem for revolved objects, a critical but under-researched area in subtractive manufacturing. We propose a new carvable coarsening hull and a packing strategy that uses beam search and a bottom-up placement method to position these hulls in the stock material. Our method was tested on diverse sets of revolved objects with different geometries, and physical tests were conducted on a 5-axis machining platform, proving its ability to enhance material use and manufacturability.</div></div>","PeriodicalId":55083,"journal":{"name":"Graphical Models","volume":"141 ","pages":"Article 101282"},"PeriodicalIF":2.2,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144779312","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 : 2025-09-01Epub Date: 2025-08-13DOI: 10.1016/j.gmod.2025.101295
Xuhai Chen , Guangze Zhang , Wanyi Wang , Juan Cao , Zhonggui Chen
Vector graphics are widely used in areas such as logo design and digital painting, including both stroked and filled paths as primitives. GPU-based rendering for filled paths already has well-established solutions. Due to the complexity of stroked paths, existing methods often render them by approximating strokes with filled shapes. However, the performance of existing methods still leaves room for improvement. This paper designs a GPU-accelerated rendering algorithm along with a curvature-guided parallel adaptive subdivision method to accurately and efficiently render stroke areas. Additionally, we propose an efficient Newton iteration-based method for arc-length parameterization of quadratic curves, along with an error estimation technique. This enables a parallel rendering approach for dashed stroke styles and arc-length guided texture filling. Experimental results show that our method achieves average speedups of for rendering quadratic stroked paths and for rendering quadratic dashed strokes, compared to the best existing approaches.
{"title":"GPU-accelerated rendering of vector strokes with piecewise quadratic approximation","authors":"Xuhai Chen , Guangze Zhang , Wanyi Wang , Juan Cao , Zhonggui Chen","doi":"10.1016/j.gmod.2025.101295","DOIUrl":"10.1016/j.gmod.2025.101295","url":null,"abstract":"<div><div>Vector graphics are widely used in areas such as logo design and digital painting, including both stroked and filled paths as primitives. GPU-based rendering for filled paths already has well-established solutions. Due to the complexity of stroked paths, existing methods often render them by approximating strokes with filled shapes. However, the performance of existing methods still leaves room for improvement. This paper designs a GPU-accelerated rendering algorithm along with a curvature-guided parallel adaptive subdivision method to accurately and efficiently render stroke areas. Additionally, we propose an efficient Newton iteration-based method for arc-length parameterization of quadratic curves, along with an error estimation technique. This enables a parallel rendering approach for dashed stroke styles and arc-length guided texture filling. Experimental results show that our method achieves average speedups of <span><math><mrow><mn>3</mn><mo>.</mo><mn>4</mn><mo>×</mo></mrow></math></span> for rendering quadratic stroked paths and <span><math><mrow><mn>2</mn><mo>.</mo><mn>5</mn><mo>×</mo></mrow></math></span> for rendering quadratic dashed strokes, compared to the best existing approaches.</div></div>","PeriodicalId":55083,"journal":{"name":"Graphical Models","volume":"141 ","pages":"Article 101295"},"PeriodicalIF":2.2,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144829843","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 : 2025-09-01Epub Date: 2025-08-14DOI: 10.1016/j.gmod.2025.101294
Ran Chen , Xiang Xu , KaiYao Ge , Yanning Xu , Xiangxu Meng , Lu Wang
Soft shadows play a crucial role in enhancing visual realism in real-time rendering. Although traditional shadow mapping techniques offer high efficiency, they often suffer from artifacts and limited quality. In contrast, ray tracing can produce high-fidelity soft shadows but incurs substantial computational cost. In this paper, we propose a general-purpose, real-time soft shadow generation method based on neural networks. To encode shadow geometry, we employ the hard shadows via shadow mapping as input to our network, which effectively captures the spatial layout of shadow positions and contours. A lightweight U-Net architecture then refines this input to synthesize high-quality soft shadows in real time. The generated shadows closely approximate ray-traced references in visual fidelity. Compared to existing learning-based methods, our approach produces higher-quality soft shadows and offers improved generalization across diverse scenes. Furthermore, it requires no scene-specific precomputation, making it directly applicable to practical real-time rendering scenarios.
{"title":"Real-time neural soft shadow synthesis from hard shadows","authors":"Ran Chen , Xiang Xu , KaiYao Ge , Yanning Xu , Xiangxu Meng , Lu Wang","doi":"10.1016/j.gmod.2025.101294","DOIUrl":"10.1016/j.gmod.2025.101294","url":null,"abstract":"<div><div>Soft shadows play a crucial role in enhancing visual realism in real-time rendering. Although traditional shadow mapping techniques offer high efficiency, they often suffer from artifacts and limited quality. In contrast, ray tracing can produce high-fidelity soft shadows but incurs substantial computational cost. In this paper, we propose a general-purpose, real-time soft shadow generation method based on neural networks. To encode shadow geometry, we employ the hard shadows via shadow mapping as input to our network, which effectively captures the spatial layout of shadow positions and contours. A lightweight U-Net architecture then refines this input to synthesize high-quality soft shadows in real time. The generated shadows closely approximate ray-traced references in visual fidelity. Compared to existing learning-based methods, our approach produces higher-quality soft shadows and offers improved generalization across diverse scenes. Furthermore, it requires no scene-specific precomputation, making it directly applicable to practical real-time rendering scenarios.</div></div>","PeriodicalId":55083,"journal":{"name":"Graphical Models","volume":"141 ","pages":"Article 101294"},"PeriodicalIF":2.2,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144842156","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 : 2025-09-01Epub Date: 2025-08-27DOI: 10.1016/j.gmod.2025.101301
Haosen Fu, Mingcong Ma, Junqiu Zhu, Lu Wang, Yanning Xu
With the proliferation of mobile hardware-accelerated ray tracing, visual quality at low sampling rates (1spp) significantly deteriorates due to high-frequency noise and temporal artifacts introduced by Monte Carlo path tracing. Traditional spatiotemporal denoising methods, such as Spatiotemporal Variance-Guided Filtering (SVGF), effectively suppress noise by fusing multi-frame information and using geometry buffer (G-buffer) guided filters. However, their reliance on per-frame variance computation and global filtering imposes prohibitive overhead for mobile devices. This paper proposes an edge-aware, data-driven real-time denoising architecture within the SVGF framework, tailored explicitly for mobile computational constraints. Our method introduces two key innovations that eliminate variance estimation overhead: (1) an adaptive filtering kernel sizing mechanism, which dynamically adjusts filtering scope based on local complexity analysis of the G-buffer; and (2) a data-driven weight table construction strategy, converting traditional computational processes into efficient real-time lookup operations. These innovations significantly enhance processing efficiency while preserving edge accuracy. Experimental results on the Qualcomm Snapdragon 768G platform demonstrate that our method achieves 55 FPS with 1spp input. This frame rate is 67.42% higher than mobile-optimized SVGF, provides better visual quality, and reduces power consumption by 16.80%. Our solution offers a practical and efficient denoising framework suitable for real-time ray tracing in mobile gaming and AR/VR applications.
{"title":"Edge-aware denoising framework for real-time mobile ray tracing","authors":"Haosen Fu, Mingcong Ma, Junqiu Zhu, Lu Wang, Yanning Xu","doi":"10.1016/j.gmod.2025.101301","DOIUrl":"10.1016/j.gmod.2025.101301","url":null,"abstract":"<div><div>With the proliferation of mobile hardware-accelerated ray tracing, visual quality at low sampling rates (1spp) significantly deteriorates due to high-frequency noise and temporal artifacts introduced by Monte Carlo path tracing. Traditional spatiotemporal denoising methods, such as Spatiotemporal Variance-Guided Filtering (SVGF), effectively suppress noise by fusing multi-frame information and using geometry buffer (G-buffer) guided filters. However, their reliance on per-frame variance computation and global filtering imposes prohibitive overhead for mobile devices. This paper proposes an edge-aware, data-driven real-time denoising architecture within the SVGF framework, tailored explicitly for mobile computational constraints. Our method introduces two key innovations that eliminate variance estimation overhead: (1) an adaptive filtering kernel sizing mechanism, which dynamically adjusts filtering scope based on local complexity analysis of the G-buffer; and (2) a data-driven weight table construction strategy, converting traditional computational processes into efficient real-time lookup operations. These innovations significantly enhance processing efficiency while preserving edge accuracy. Experimental results on the Qualcomm Snapdragon 768G platform demonstrate that our method achieves 55 FPS with 1spp input. This <strong>frame rate is 67.42% higher</strong> than mobile-optimized SVGF, provides <strong>better visual quality</strong>, and <strong>reduces power consumption by 16.80%</strong>. Our solution offers a practical and efficient denoising framework suitable for real-time ray tracing in mobile gaming and AR/VR applications.</div></div>","PeriodicalId":55083,"journal":{"name":"Graphical Models","volume":"141 ","pages":"Article 101301"},"PeriodicalIF":2.2,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144904092","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 : 2025-09-01Epub Date: 2025-08-22DOI: 10.1016/j.gmod.2025.101289
Chang Liu , Chao Liu , Yuming Zhang , Zhongqi Wu , Jianwei Guo
3D registration methods based on point-level information struggle in situations with noise, density variation, large-scale points, and small overlaps, while existing primitive-based methods are usually sensitive to tiny errors in the primitive extraction process. In this paper, we present a reliable and efficient global registration algorithm exploiting the RANdom SAmple Consensus (RANSAC) in the plane space instead of the point space. To improve the inlier ratio in the putative correspondences, we design an inner plane-based descriptor, termed Convex Hull Descriptor (CHD), and an inter plane-based descriptor, termed PLane Feature Histograms (PLFH), which take full advantage of plane contour shape and plane-wise relationship, respectively. Based on those new descriptors, we randomly select corresponding plane pairs to compute candidate transformations, followed by a hypotheses verification step to identify the optimal registration. Extensive tests on large-scale point sets demonstrate the effectiveness of our method, and that it notably improves registration performance compared to state-of-the-art methods in terms of efficiency and accuracy.
{"title":"Efficient RANSAC in 4D Plane Space for Point Cloud Registration","authors":"Chang Liu , Chao Liu , Yuming Zhang , Zhongqi Wu , Jianwei Guo","doi":"10.1016/j.gmod.2025.101289","DOIUrl":"10.1016/j.gmod.2025.101289","url":null,"abstract":"<div><div>3D registration methods based on point-level information struggle in situations with noise, density variation, large-scale points, and small overlaps, while existing primitive-based methods are usually sensitive to tiny errors in the primitive extraction process. In this paper, we present a reliable and efficient global registration algorithm exploiting the RANdom SAmple Consensus (RANSAC) in the plane space instead of the point space. To improve the inlier ratio in the putative correspondences, we design an inner plane-based descriptor, termed <em>Convex Hull Descriptor</em> (CHD), and an inter plane-based descriptor, termed <em>PLane Feature Histograms</em> (PLFH), which take full advantage of plane contour shape and plane-wise relationship, respectively. Based on those new descriptors, we randomly select corresponding plane pairs to compute candidate transformations, followed by a hypotheses verification step to identify the optimal registration. Extensive tests on large-scale point sets demonstrate the effectiveness of our method, and that it notably improves registration performance compared to state-of-the-art methods in terms of efficiency and accuracy.</div></div>","PeriodicalId":55083,"journal":{"name":"Graphical Models","volume":"141 ","pages":"Article 101289"},"PeriodicalIF":2.2,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144886852","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 : 2025-09-01Epub Date: 2025-08-05DOI: 10.1016/j.gmod.2025.101285
Zichen Xi , Zhihao Yao , Jiahui Huang , Zi-Qi Lu , Hongyu Yan , Tai-Jiang Mu , Zhigang Wang , Qun-Ce Xu
Automated generation of large-scale 3D scenes presents a significant challenge due to the resource-intensive training and datasets required. This is in sharp contrast to the 2D counterparts that have become readily available due to their superior speed and quality. However, prior work in 3D procedural modeling has demonstrated promise in generating high-quality assets using the combination of algorithms and user-defined rules. To leverage the best of both 2D generative models and procedural modeling tools, we present TerraCraft, a novel framework for generating geometrically high-quality 3D city-scale scenes. By utilizing Large Language Models (LLMs), TerraCraft can generate city-scale 3D scenes from natural text descriptions. With its intuitive operation and powerful capabilities, TerraCraft enables users to easily create geometrically high-quality scenes readily for various applications, such as virtual reality and game design. We validate TerraCraft’s effectiveness through extensive experiments and user studies, showing its superior performance compared to existing baselines.
{"title":"TerraCraft: City-scale generative procedural modeling with natural languages","authors":"Zichen Xi , Zhihao Yao , Jiahui Huang , Zi-Qi Lu , Hongyu Yan , Tai-Jiang Mu , Zhigang Wang , Qun-Ce Xu","doi":"10.1016/j.gmod.2025.101285","DOIUrl":"10.1016/j.gmod.2025.101285","url":null,"abstract":"<div><div>Automated generation of large-scale 3D scenes presents a significant challenge due to the resource-intensive training and datasets required. This is in sharp contrast to the 2D counterparts that have become readily available due to their superior speed and quality. However, prior work in 3D procedural modeling has demonstrated promise in generating high-quality assets using the combination of algorithms and user-defined rules. To leverage the best of both 2D generative models and procedural modeling tools, we present TerraCraft, a novel framework for generating geometrically high-quality 3D city-scale scenes. By utilizing Large Language Models (LLMs), TerraCraft can generate city-scale 3D scenes from natural text descriptions. With its intuitive operation and powerful capabilities, TerraCraft enables users to easily create geometrically high-quality scenes readily for various applications, such as virtual reality and game design. We validate TerraCraft’s effectiveness through extensive experiments and user studies, showing its superior performance compared to existing baselines.</div></div>","PeriodicalId":55083,"journal":{"name":"Graphical Models","volume":"141 ","pages":"Article 101285"},"PeriodicalIF":2.2,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144771658","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 : 2025-09-01Epub Date: 2025-08-15DOI: 10.1016/j.gmod.2025.101292
Ye Wang , Ruiqi Liu , Xuping Xie , Lanjun Wang , Zili Yi , Rui Ma
With the growing popularity of personalized human content creation and sharing, there is a rising demand for advanced techniques in customized human image generation. However, current methods struggle to simultaneously maintain the fidelity of human identity and ensure the consistency of textual prompts, often resulting in suboptimal outcomes. This shortcoming is primarily due to the lack of effective constraints during the simultaneous integration of visual and textual prompts, leading to unhealthy mutual interference that compromises the full expression of both types of input. Building on prior research that suggests visual and textual conditions influence different regions of an image in distinct ways, we introduce a novel Dual-Pathway Adapter (DP-Adapter) to enhance both high-fidelity identity preservation and textual consistency in personalized human image generation. Our approach begins by decoupling the target human image into visually sensitive and text-sensitive regions. For visually sensitive regions, DP-Adapter employs an Identity-Enhancing Adapter (IEA) to preserve detailed identity features. For text-sensitive regions, we introduce a Textual-Consistency Adapter (TCA) to minimize visual interference and ensure the consistency of textual semantics. To seamlessly integrate these pathways, we develop a Fine-Grained Feature-Level Blending (FFB) module that efficiently combines hierarchical semantic features from both pathways, resulting in more natural and coherent synthesis outcomes. Additionally, DP-Adapter supports various innovative applications, including controllable headshot-to-full-body portrait generation, age editing, old-photo to reality, and expression editing. Extensive experiments demonstrate that DP-Adapter outperforms state-of-the-art methods in both visual fidelity and text consistency, highlighting its effectiveness and versatility in the field of human image generation.
{"title":"DP-Adapter: Dual-pathway adapter for boosting fidelity and text consistency in customizable human image generation","authors":"Ye Wang , Ruiqi Liu , Xuping Xie , Lanjun Wang , Zili Yi , Rui Ma","doi":"10.1016/j.gmod.2025.101292","DOIUrl":"10.1016/j.gmod.2025.101292","url":null,"abstract":"<div><div>With the growing popularity of personalized human content creation and sharing, there is a rising demand for advanced techniques in customized human image generation. However, current methods struggle to simultaneously maintain the fidelity of human identity and ensure the consistency of textual prompts, often resulting in suboptimal outcomes. This shortcoming is primarily due to the lack of effective constraints during the simultaneous integration of visual and textual prompts, leading to unhealthy mutual interference that compromises the full expression of both types of input. Building on prior research that suggests visual and textual conditions influence different regions of an image in distinct ways, we introduce a novel Dual-Pathway Adapter (DP-Adapter) to enhance both high-fidelity identity preservation and textual consistency in personalized human image generation. Our approach begins by decoupling the target human image into visually sensitive and text-sensitive regions. For visually sensitive regions, DP-Adapter employs an Identity-Enhancing Adapter (IEA) to preserve detailed identity features. For text-sensitive regions, we introduce a Textual-Consistency Adapter (TCA) to minimize visual interference and ensure the consistency of textual semantics. To seamlessly integrate these pathways, we develop a Fine-Grained Feature-Level Blending (FFB) module that efficiently combines hierarchical semantic features from both pathways, resulting in more natural and coherent synthesis outcomes. Additionally, DP-Adapter supports various innovative applications, including controllable headshot-to-full-body portrait generation, age editing, old-photo to reality, and expression editing. Extensive experiments demonstrate that DP-Adapter outperforms state-of-the-art methods in both visual fidelity and text consistency, highlighting its effectiveness and versatility in the field of human image generation.</div></div>","PeriodicalId":55083,"journal":{"name":"Graphical Models","volume":"141 ","pages":"Article 101292"},"PeriodicalIF":2.2,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144842158","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 : 2025-09-01Epub Date: 2025-08-17DOI: 10.1016/j.gmod.2025.101287
Bowei Jiang , Tongyuan Bai , Peng Zheng , Tieru Wu , Rui Ma
The integration of embodied intelligence in indoor scene synthesis holds significant potential for future interior design applications. Nevertheless, prevailing methodologies for indoor scene synthesis predominantly adhere to data-driven learning paradigms. Despite achieving photorealistic 3D renderings through such approaches, current frameworks systematically neglect to incorporate agent-centric functional metrics essential for optimizing navigational topology and task-oriented interactivity in embodied AI systems like service robotics platforms or autonomous domestic assistants. For example, poorly arranged furniture may prevent robots from effectively interacting with the environment, and this issue cannot be fully resolved by merely introducing prior constraints. To fill this gap, we propose Nav2Scene, a novel plug-and-play fine-tuning mechanism that can be deployed on existing scene generators to enhance the suitability of generated scenes for efficient robot navigation. Specifically, we first introduce path planning score (PPS), which is defined based on the results of the path planning algorithm and can be used to evaluate the robot navigation suitability of a given scene. Then, we pre-compute the PPS of 3D scenes from existing datasets and train a ScoreNet to efficiently predict the PPS of the generated scenes. Finally, the predicted PPS is used to guide the fine-tuning of existing scene generators and produce indoor scenes with higher PPS, indicating improved suitability for robot navigation. We conduct experiments on the 3D-FRONT dataset for different tasks including scene generation, completion and re-arrangement. The results demonstrate that by incorporating our Nav2Scene mechanism, the fine-tuned scene generators can produce scenes with improved navigation compatibility for home robots, while maintaining superior or comparable performance in terms of scene quality and diversity.
{"title":"Nav2Scene: Navigation-driven fine-tuning for robot-friendly scene generation","authors":"Bowei Jiang , Tongyuan Bai , Peng Zheng , Tieru Wu , Rui Ma","doi":"10.1016/j.gmod.2025.101287","DOIUrl":"10.1016/j.gmod.2025.101287","url":null,"abstract":"<div><div>The integration of embodied intelligence in indoor scene synthesis holds significant potential for future interior design applications. Nevertheless, prevailing methodologies for indoor scene synthesis predominantly adhere to data-driven learning paradigms. Despite achieving photorealistic 3D renderings through such approaches, current frameworks systematically neglect to incorporate agent-centric functional metrics essential for optimizing navigational topology and task-oriented interactivity in embodied AI systems like service robotics platforms or autonomous domestic assistants. For example, poorly arranged furniture may prevent robots from effectively interacting with the environment, and this issue cannot be fully resolved by merely introducing prior constraints. To fill this gap, we propose Nav2Scene, a novel plug-and-play fine-tuning mechanism that can be deployed on existing scene generators to enhance the suitability of generated scenes for efficient robot navigation. Specifically, we first introduce path planning score (PPS), which is defined based on the results of the path planning algorithm and can be used to evaluate the robot navigation suitability of a given scene. Then, we pre-compute the PPS of 3D scenes from existing datasets and train a ScoreNet to efficiently predict the PPS of the generated scenes. Finally, the predicted PPS is used to guide the fine-tuning of existing scene generators and produce indoor scenes with higher PPS, indicating improved suitability for robot navigation. We conduct experiments on the 3D-FRONT dataset for different tasks including scene generation, completion and re-arrangement. The results demonstrate that by incorporating our Nav2Scene mechanism, the fine-tuned scene generators can produce scenes with improved navigation compatibility for home robots, while maintaining superior or comparable performance in terms of scene quality and diversity.</div></div>","PeriodicalId":55083,"journal":{"name":"Graphical Models","volume":"141 ","pages":"Article 101287"},"PeriodicalIF":2.2,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144858475","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 : 2025-08-01Epub Date: 2025-06-19DOI: 10.1016/j.gmod.2025.101275
Erkan Gunpinar , A. Alper Tasmektepligil , Márton Vaitkus , Péter Salvi
This work investigates ribbon-based multi-sided surfaces that satisfy positional and cross-derivative constraints to ensure smooth transitions with adjacent tensor-product and multi-sided surfaces. The influence of cross-derivatives, crucial to surface quality, is studied within Kato’s transfinite surface interpolation instead of control point-based methods. To enhance surface quality, the surface is optimized using cost functions based on curvature metrics. Specifically, a Gaussian curvature-based cost function is also proposed in this work. An automated optimization procedure is introduced to determine rotation angles of cross-derivatives around normals and their magnitudes along curves in Kato’s interpolation scheme. Experimental results using both primitive (e.g., spherical) and realistic examples highlight the effectiveness of the proposed approach in improving surface quality.
{"title":"Optimization of cross-derivatives for ribbon-based multi-sided surfaces","authors":"Erkan Gunpinar , A. Alper Tasmektepligil , Márton Vaitkus , Péter Salvi","doi":"10.1016/j.gmod.2025.101275","DOIUrl":"10.1016/j.gmod.2025.101275","url":null,"abstract":"<div><div>This work investigates ribbon-based multi-sided surfaces that satisfy positional and cross-derivative constraints to ensure smooth transitions with adjacent tensor-product and multi-sided surfaces. The influence of cross-derivatives, crucial to surface quality, is studied within Kato’s transfinite surface interpolation instead of control point-based methods. To enhance surface quality, the surface is optimized using cost functions based on curvature metrics. Specifically, a Gaussian curvature-based cost function is also proposed in this work. An automated optimization procedure is introduced to determine rotation angles of cross-derivatives around normals and their magnitudes along curves in Kato’s interpolation scheme. Experimental results using both primitive (e.g., spherical) and realistic examples highlight the effectiveness of the proposed approach in improving surface quality.</div></div>","PeriodicalId":55083,"journal":{"name":"Graphical Models","volume":"140 ","pages":"Article 101275"},"PeriodicalIF":2.5,"publicationDate":"2025-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144314599","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 : 2025-08-01Epub Date: 2025-06-17DOI: 10.1016/j.gmod.2025.101272
Megha Shastry , Ye Fan , Clarissa Martins , Dinesh K. Pai
Fit and sizing of clothing are fundamental problems in the field of garment design, manufacture, and retail. Here we propose new computational methods for adjusting the fit of clothing on realistic models of the human body by interactively modifying desired fit attributes. Clothing fit represents the relationship between the body and the garment, and can be quantified using physical fit attributes such as ease and pressure on the body. However, the relationship between pattern geometry and such fit attributes is notoriously complex and nonlinear, requiring deep pattern making expertise to adjust patterns to achieve fit goals. Such attributes can be computed by physically based simulations, using soft avatars. Here we propose a method to learn the relationship between the fit attributes and the space of 2D pattern edits. We demonstrate our method via interactive tools that directly edit fit attributes in 3D and instantaneously predict the corresponding pattern adjustments. The approach has been tested with a range of garment types, and validated by comparing with physical prototypes. Our method introduces an alternative way to directly express fit adjustment goals, making pattern adjustment more broadly accessible. As an additional benefit, the proposed approach allows pattern adjustments to be systematized, enabling better communication and audit of decisions.
{"title":"Goal-oriented 3D pattern adjustment with machine learning","authors":"Megha Shastry , Ye Fan , Clarissa Martins , Dinesh K. Pai","doi":"10.1016/j.gmod.2025.101272","DOIUrl":"10.1016/j.gmod.2025.101272","url":null,"abstract":"<div><div>Fit and sizing of clothing are fundamental problems in the field of garment design, manufacture, and retail. Here we propose new computational methods for adjusting the fit of clothing on realistic models of the human body by interactively modifying desired <em>fit attributes</em>. Clothing fit represents the relationship between the body and the garment, and can be quantified using physical fit attributes such as ease and pressure on the body. However, the relationship between pattern geometry and such fit attributes is notoriously complex and nonlinear, requiring deep pattern making expertise to adjust patterns to achieve fit goals. Such attributes can be computed by physically based simulations, using soft avatars. Here we propose a method to learn the relationship between the fit attributes and the space of 2D pattern edits. We demonstrate our method via interactive tools that directly edit fit attributes in 3D and instantaneously predict the corresponding pattern adjustments. The approach has been tested with a range of garment types, and validated by comparing with physical prototypes. Our method introduces an alternative way to directly express fit adjustment goals, making pattern adjustment more broadly accessible. As an additional benefit, the proposed approach allows pattern adjustments to be systematized, enabling better communication and audit of decisions.</div></div>","PeriodicalId":55083,"journal":{"name":"Graphical Models","volume":"140 ","pages":"Article 101272"},"PeriodicalIF":2.5,"publicationDate":"2025-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144298108","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