Pub Date : 2025-09-23DOI: 10.1016/j.gmod.2025.101298
Hao-Xuan Song , Yue Qian , Xiaohang Zhan , Tai-Jiang Mu
3D facial animation of digital avatars driven by RGB videos has extensive applications. However, the practical implementation encounters a significant challenge due to the various identities and environments of in-the-wild videos and varying rigging designs. The traditional industry pipeline necessitates a labor-intensive alignment process to ensure compatibility, while the recent novel methods are constrained to a specific rigging standard or require additional labor on actor videos, making them difficult to apply to customized riggings and in-the-wild videos. To make the task easy and convenient, we introduce EasyAnim, which utilizes abundant 2D videos to learn an aligned implicit motion flow unsupervisedly and maps it to various rigging parameters in a generalized manner. A novel framework with self- and cross- reconstruction constraints is proposed to ensure the alignment of avatar and human actor domains. Extensive experiments demonstrate that EasyAnim generates comparable or even better results with no additional constraints and labor.
{"title":"EasyAnim: 3D facial animation from in-the-wild videos for avatars with customized riggings","authors":"Hao-Xuan Song , Yue Qian , Xiaohang Zhan , Tai-Jiang Mu","doi":"10.1016/j.gmod.2025.101298","DOIUrl":"10.1016/j.gmod.2025.101298","url":null,"abstract":"<div><div>3D facial animation of digital avatars driven by RGB videos has extensive applications. However, the practical implementation encounters a significant challenge due to the various identities and environments of in-the-wild videos and varying rigging designs. The traditional industry pipeline necessitates a labor-intensive alignment process to ensure compatibility, while the recent novel methods are constrained to a specific rigging standard or require additional labor on actor videos, making them difficult to apply to customized riggings and in-the-wild videos. To make the task easy and convenient, we introduce <strong>EasyAnim</strong>, which utilizes abundant 2D videos to learn an aligned implicit motion flow unsupervisedly and maps it to various rigging parameters in a generalized manner. A novel framework with self- and cross- reconstruction constraints is proposed to ensure the alignment of avatar and human actor domains. Extensive experiments demonstrate that EasyAnim generates comparable or even better results with no additional constraints and labor.</div></div>","PeriodicalId":55083,"journal":{"name":"Graphical Models","volume":"142 ","pages":"Article 101298"},"PeriodicalIF":2.2,"publicationDate":"2025-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145121305","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 : 2025-08-27DOI: 10.1016/j.gmod.2025.101299
L. Rocca , F. Iuricich , E. Puppo
We consider 2D scalar fields sampled on a regular grid. When the gradient is low relative to the resolution of the dataset’s range, the signal may contain flat spots: connected areas where all points share the same value. Flat spots hinder certain analyses, such as topological characterization or drainage network computations. We present an algorithm to determine a symbolic slope inside flat spots and consistently place a minimal set of critical points, in a way that is less biased than state-of-the-art methods. We present experimental results on both synthetic and real data, demonstrating how our method provides a more plausible positioning of critical points and a better recovery of the Morse–Smale complex.
{"title":"Disambiguating flat spots in discrete scalar fields","authors":"L. Rocca , F. Iuricich , E. Puppo","doi":"10.1016/j.gmod.2025.101299","DOIUrl":"10.1016/j.gmod.2025.101299","url":null,"abstract":"<div><div>We consider 2D scalar fields sampled on a regular grid. When the gradient is low relative to the resolution of the dataset’s range, the signal may contain <em>flat spots</em>: connected areas where all points share the same value. Flat spots hinder certain analyses, such as topological characterization or drainage network computations. We present an algorithm to determine a symbolic slope inside flat spots and consistently place a minimal set of critical points, in a way that is less biased than state-of-the-art methods. We present experimental results on both synthetic and real data, demonstrating how our method provides a more plausible positioning of critical points and a better recovery of the Morse–Smale complex.</div></div>","PeriodicalId":55083,"journal":{"name":"Graphical Models","volume":"141 ","pages":"Article 101299"},"PeriodicalIF":2.2,"publicationDate":"2025-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144904093","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 : 2025-08-27DOI: 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":"2025-08-27","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 : 2025-08-25DOI: 10.1016/j.gmod.2025.101300
Hai Yuan , Xia Yuan , Yanli Liu , Guanyu Xing , Jing Hu , Xi Wu , Zijun Zhou
Virtual human avatars are essential for applications such as gaming, augmented reality, and virtual production. However, existing methods struggle to achieve high fidelity reconstruction from monocular input while keeping hardware costs low. Many approaches rely on the SMPL body prior and apply vertex offsets to represent clothed avatars. Unfortunately, excessive offsets often cause misalignment and blurred contours, particularly around clothing wrinkles, silhouette boundaries, and facial regions. To address these limitations, we propose a dual branch framework for human avatar reconstruction from monocular video. A lightweight Vertex Align Net (VAN) predicts per-vertex normal direction offsets on the SMPL mesh to achieve coarse geometric alignment and guide Gaussian-based human avatar modeling. In parallel, we construct a high resolution facial Gaussian branch based on FLAME estimated parameters, with facial regions localized via pretrained detectors. The facial and body renderings are fused using a semantic mask to enhance facial clarity and ensure globally consistent avatar appearance. Experiments demonstrate that our method surpasses state of the art approaches in modeling animatable human avatars with fine grained fidelity.
{"title":"Adaptive mesh-aligned Gaussian Splatting for monocular human avatar reconstruction","authors":"Hai Yuan , Xia Yuan , Yanli Liu , Guanyu Xing , Jing Hu , Xi Wu , Zijun Zhou","doi":"10.1016/j.gmod.2025.101300","DOIUrl":"10.1016/j.gmod.2025.101300","url":null,"abstract":"<div><div>Virtual human avatars are essential for applications such as gaming, augmented reality, and virtual production. However, existing methods struggle to achieve high fidelity reconstruction from monocular input while keeping hardware costs low. Many approaches rely on the SMPL body prior and apply vertex offsets to represent clothed avatars. Unfortunately, excessive offsets often cause misalignment and blurred contours, particularly around clothing wrinkles, silhouette boundaries, and facial regions. To address these limitations, we propose a dual branch framework for human avatar reconstruction from monocular video. A lightweight Vertex Align Net (VAN) predicts per-vertex normal direction offsets on the SMPL mesh to achieve coarse geometric alignment and guide Gaussian-based human avatar modeling. In parallel, we construct a high resolution facial Gaussian branch based on FLAME estimated parameters, with facial regions localized via pretrained detectors. The facial and body renderings are fused using a semantic mask to enhance facial clarity and ensure globally consistent avatar appearance. Experiments demonstrate that our method surpasses state of the art approaches in modeling animatable human avatars with fine grained fidelity.</div></div>","PeriodicalId":55083,"journal":{"name":"Graphical Models","volume":"141 ","pages":"Article 101300"},"PeriodicalIF":2.2,"publicationDate":"2025-08-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144893147","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 : 2025-08-22DOI: 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":"2025-08-22","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 : 2025-08-21DOI: 10.1016/j.gmod.2025.101284
Hang Zhao , Kexiong Yu , Yuhang Huang , Renjiao Yi , Chenyang Zhu , Kai Xu
Combinatorial Optimization (CO) problems are fundamentally important in numerous real-world applications across diverse industries, notably computer graphics, characterized by entailing enormous solution space and demanding time-sensitive response. Despite recent advancements in neural solvers, their limited expressiveness struggles to capture the multi-modal nature of CO landscapes. While some research has adopted diffusion models, these methods sample solutions indiscriminately from the entire NP-complete solution space with time-consuming denoising processes, limiting scalability for large-scale problems. We propose DISCO, an efficient DIffusion Solver for large-scale Combinatorial Optimization problems that excels in both solution quality and inference speed. DISCO’s efficacy is twofold: First, it enhances solution quality by constraining the sampling space to a more meaningful domain guided by solution residues, while preserving the multi-modal properties of the output distributions. Second, it accelerates the denoising process through an analytically solvable approach, enabling solution sampling with very few reverse-time steps and significantly reducing inference time. This inference-speed advantage is further amplified by Jittor, a high-performance learning framework based on just-in-time compiling and meta-operators. DISCO delivers strong performance on large-scale Traveling Salesman Problems and challenging Maximal Independent Set benchmarks, with inference duration up to 5.38 times faster than existing diffusion solver alternatives. We apply DISCO to design 2D/3D TSP Art, enabling the generation of fluid stroke sequences at reduced path costs. By incorporating DISCO’s multi-modal property into a divide-and-conquer strategy, it can further generalize to solve unseen-scale instances out of the box.
{"title":"DISCO: Efficient Diffusion Solver for large-scale Combinatorial Optimization problems","authors":"Hang Zhao , Kexiong Yu , Yuhang Huang , Renjiao Yi , Chenyang Zhu , Kai Xu","doi":"10.1016/j.gmod.2025.101284","DOIUrl":"10.1016/j.gmod.2025.101284","url":null,"abstract":"<div><div>Combinatorial Optimization (CO) problems are fundamentally important in numerous real-world applications across diverse industries, notably computer graphics, characterized by entailing enormous solution space and demanding time-sensitive response. Despite recent advancements in neural solvers, their limited expressiveness struggles to capture the multi-modal nature of CO landscapes. While some research has adopted diffusion models, these methods sample solutions indiscriminately from the entire NP-complete solution space with time-consuming denoising processes, limiting scalability for large-scale problems. We propose <strong>DISCO</strong>, an efficient <strong>DI</strong>ffusion <strong>S</strong>olver for large-scale <strong>C</strong>ombinatorial <strong>O</strong>ptimization problems that excels in both solution quality and inference speed. DISCO’s efficacy is twofold: First, it enhances solution quality by constraining the sampling space to a more meaningful domain guided by solution residues, while preserving the multi-modal properties of the output distributions. Second, it accelerates the denoising process through an analytically solvable approach, enabling solution sampling with very few reverse-time steps and significantly reducing inference time. This inference-speed advantage is further amplified by Jittor, a high-performance learning framework based on just-in-time compiling and meta-operators. DISCO delivers strong performance on large-scale Traveling Salesman Problems and challenging Maximal Independent Set benchmarks, with inference duration up to 5.38 times faster than existing diffusion solver alternatives. We apply DISCO to design 2D/3D TSP Art, enabling the generation of fluid stroke sequences at reduced path costs. By incorporating DISCO’s multi-modal property into a divide-and-conquer strategy, it can further generalize to solve unseen-scale instances out of the box.</div></div>","PeriodicalId":55083,"journal":{"name":"Graphical Models","volume":"141 ","pages":"Article 101284"},"PeriodicalIF":2.2,"publicationDate":"2025-08-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144878547","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 : 2025-08-19DOI: 10.1016/j.gmod.2025.101293
Jia-Hong Liu , Shao-Kui Zhang , Shuran Sun , Zihao Wang , Song-Hai Zhang
Recently, indoor scene synthesis has gathered significant attention, leading to the development of numerous indoor datasets. However, existing datasets only address static furniture and scenes, ignoring the need for dynamic interior design scenarios that emphasize flexible functionalities. Addressing this gap, we present DIFF (Dataset for Indoor Flexible Furniture), featuring expertly crafted and labeled furniture modules capable of inter-transforming between different states, e.g., a cabinet can be inter-transformed to a desk. Each module exhibits flexibility in shifting to multiple shapes and functionalities. Additionally, we propose a method that adapts our dataset to generate flexible layouts. By matching our flexible objects to objects from existing datasets, we use a graph-based approach to migrate the spatial relation priors for optimizing a layout; subsequent layouts are then generated by minimizing a transition-cost function. Analyses and user studies validate the quality of our modules and demonstrate the plausibility of the proposed method.
{"title":"DIFF: A dataset for indoor flexible furniture","authors":"Jia-Hong Liu , Shao-Kui Zhang , Shuran Sun , Zihao Wang , Song-Hai Zhang","doi":"10.1016/j.gmod.2025.101293","DOIUrl":"10.1016/j.gmod.2025.101293","url":null,"abstract":"<div><div>Recently, indoor scene synthesis has gathered significant attention, leading to the development of numerous indoor datasets. However, existing datasets only address static furniture and scenes, ignoring the need for dynamic interior design scenarios that emphasize flexible functionalities. Addressing this gap, we present DIFF (Dataset for Indoor Flexible Furniture), featuring expertly crafted and labeled furniture modules capable of inter-transforming between different states, e.g., a cabinet can be inter-transformed to a desk. Each module exhibits flexibility in shifting to multiple shapes and functionalities. Additionally, we propose a method that adapts our dataset to generate flexible layouts. By matching our flexible objects to objects from existing datasets, we use a graph-based approach to migrate the spatial relation priors for optimizing a layout; subsequent layouts are then generated by minimizing a transition-cost function. Analyses and user studies validate the quality of our modules and demonstrate the plausibility of the proposed method.</div></div>","PeriodicalId":55083,"journal":{"name":"Graphical Models","volume":"141 ","pages":"Article 101293"},"PeriodicalIF":2.2,"publicationDate":"2025-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144867141","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 : 2025-08-17DOI: 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":"2025-08-17","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 : 2025-08-15DOI: 10.1016/j.gmod.2025.101297
Hao Yu , Longdu Liu , Shuangmin Chen , Lin Lu , Yuanfeng Zhou , Shiqing Xin , Changhe Tu
The rapid evolution of digital orthodontics has highlighted a critical need for automated treatment planning systems that balance computational efficiency with clinical reliability. However, existing methods still suffer from several limitations, including excessive clinician involvement (accounting for over 35% of treatment planning time), reliance on empirically defined key frames, and limited biomechanical plausibility, particularly in cases of severe dental crowding. This paper proposes a novel collision-free optimization framework to address these issues simultaneously. Our method defines a total movement energy function evaluated over each tooth’s pose at intermediate time frames. This energy is minimized iteratively using a steepest descent strategy. A rollback mechanism is employed: if inter-tooth penetration is detected during an update, the step size is halved repeatedly until collisions are eliminated. The framework allows flexible control over the number of intermediate frames to enforce a strict constraint on per-tooth displacement, limiting it to 0.2 mm translation or rotation every 10 to 14 days. Clinical evaluations show that the proposed algorithm can generate desirable and clinically valid tooth movement plans, even in complex cases, while significantly reducing the need for manual intervention.
{"title":"Collision-free path planning method for digital orthodontic treatment","authors":"Hao Yu , Longdu Liu , Shuangmin Chen , Lin Lu , Yuanfeng Zhou , Shiqing Xin , Changhe Tu","doi":"10.1016/j.gmod.2025.101297","DOIUrl":"10.1016/j.gmod.2025.101297","url":null,"abstract":"<div><div>The rapid evolution of digital orthodontics has highlighted a critical need for automated treatment planning systems that balance computational efficiency with clinical reliability. However, existing methods still suffer from several limitations, including excessive clinician involvement (accounting for over 35% of treatment planning time), reliance on empirically defined key frames, and limited biomechanical plausibility, particularly in cases of severe dental crowding. This paper proposes a novel collision-free optimization framework to address these issues simultaneously. Our method defines a total movement energy function evaluated over each tooth’s pose at intermediate time frames. This energy is minimized iteratively using a steepest descent strategy. A rollback mechanism is employed: if inter-tooth penetration is detected during an update, the step size is halved repeatedly until collisions are eliminated. The framework allows flexible control over the number of intermediate frames to enforce a strict constraint on per-tooth displacement, limiting it to 0.2 mm translation or <span><math><mrow><mn>2</mn><mo>°</mo></mrow></math></span> rotation every 10 to 14 days. Clinical evaluations show that the proposed algorithm can generate desirable and clinically valid tooth movement plans, even in complex cases, while significantly reducing the need for manual intervention.</div></div>","PeriodicalId":55083,"journal":{"name":"Graphical Models","volume":"141 ","pages":"Article 101297"},"PeriodicalIF":2.2,"publicationDate":"2025-08-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144842157","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 : 2025-08-15DOI: 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":"2025-08-15","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}
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