Contour
-
Corridor-based Adaptive Control Barrier and Lyapunov Functions for Safe Mobile Robot Navigation
Abstract
Safe navigation in unknown and cluttered environments remains a challenging problem in robotics. Model Predictive Contour Control (MPCC) has shown promise for performant obstacle avoidance by enabling precise and agile trajectory tracking, however, existing methods lack formal safety assurances. To address this issue, we propose a general Control Lyapunov Function (CLF) and Control Barrier Function (CBF) enabled MPCC framework that enforces safety constraints derived from a free-space corridor around the planned trajectory. To enhance feasibility, we dynamically adapt the CBF parameters at runtime using a Soft Actor-Critic (SAC) policy. The approach is validated with extensive simulations and an experiment on mobile robot navigation in unknown cluttered environments.
Abstract (translated)
在未知且复杂的环境中实现安全导航依然是机器人技术面临的一大挑战。模型预测轮廓控制（Model Predictive Contour Control，MPCC）因其能够使轨迹跟踪更加精确和灵活而显示出良好的障碍物避让性能，但现有的方法缺乏正式的安全保证措施。为解决这一问题，我们提出了一种通用的基于控制Lyapunov函数（CLF）和控制屏障函数（CBF）增强型的MPCC框架，该框架通过围绕规划轨迹形成的无障碍空间走廊来执行安全约束条件。为了提高可行性，我们在运行时动态调整CBF参数，并采用软演员评论家（SAC）策略进行优化。我们通过广泛的模拟测试以及在未知复杂环境中的移动机器人导航实验验证了这一方法的有效性。
URL
https://arxiv.org/abs/2507.14700
PDF
-
Automated Interpretation of Non-Destructive Evaluation Contour Maps Using Large Language Models for Bridge Condition Assessment
2025-07-18 17:39:03Viraj Nishesh Darji, Callie C. Liao, Duoduo LiaoAbstract
Bridge maintenance and safety are essential for transportation authorities, and Non-Destructive Evaluation (NDE) techniques are critical to assessing structural integrity. However, interpreting NDE data can be time-consuming and requires expertise, potentially delaying decision-making. Recent advancements in Large Language Models (LLMs) offer new ways to automate and improve this analysis. This pilot study introduces a holistic assessment of LLM capabilities for interpreting NDE contour maps and demonstrates the effectiveness of LLMs in providing detailed bridge condition analyses. It establishes a framework for integrating LLMs into bridge inspection workflows, indicating that LLM-assisted analysis can enhance efficiency without compromising accuracy. In this study, several LLMs are explored with prompts specifically designed to enhance the quality of image descriptions, which are applied to interpret five different NDE contour maps obtained through technologies for assessing bridge conditions. Each LLM model is evaluated based on its ability to produce detailed descriptions, identify defects, provide actionable recommendations, and demonstrate overall accuracy. The research indicates that four of the nine models provide better image descriptions, effectively covering a wide range of topics related to the bridge's condition. The outputs from these four models are summarized using five different LLMs to form a comprehensive overview of the bridge. Notably, LLMs ChatGPT-4 and Claude 3.5 Sonnet generate more effective summaries. The findings suggest that LLMs have the potential to significantly improve efficiency and accuracy. This pilot study presents an innovative approach that leverages LLMs for image captioning in parallel and summarization, enabling faster decision-making in bridge maintenance and enhancing infrastructure management and safety assessments.
Abstract (translated)
桥梁维护和安全对交通管理部门至关重要，而非破坏性评估（NDE）技术对于评估结构完整性是必不可少的。然而，解释NDE数据既耗时又需要专业知识，这可能会延误决策过程。近期在大型语言模型（LLMs）方面的进展为自动化并改进此类分析提供了新的途径。这项试点研究对LLM在解读NDE轮廓图方面的能力进行了全面评估，并展示了LLM在提供详细的桥梁状况分析中的有效性。该研究建立了一个框架，将LLM整合到桥梁检查工作流程中，表明使用LLM辅助分析可以提高效率而不会降低准确性。 在这项研究中，几种不同的LLM被探索并应用了一系列专为改善图像描述质量设计的提示语，这些提示用于解释通过不同技术获得的五种NDE轮廓图。每个模型依据其生成详细描述的能力、识别缺陷的能力、提供可操作建议的能力以及整体准确性的表现进行了评估。研究发现，九个模型中有四个提供了更好的图像描述，并且有效涵盖了与桥梁状况相关的一系列广泛话题。这四个模型的输出使用五个不同的LLM进行汇总，从而形成对整个桥梁状况的综合概述。值得注意的是，ChatGPT-4和Claude 3.5 Sonnet生成了更为有效的摘要。 该研究结果表明，LLMs有可能显著提高效率与准确性。这项试点项目提出了一种创新的方法，利用LLM并行处理图像标题生成以及汇总操作，从而加速桥梁维护的决策过程，并提升基础设施管理和安全评估的质量。
URL
https://arxiv.org/abs/2507.14107
PDF
-
DynFaceRestore: Balancing Fidelity and Quality in Diffusion-Guided Blind Face Restoration with Dynamic Blur-Level Mapping and Guidance
2025-07-18 10:16:08Huu-Phu Do, Yu-Wei Chen, Yi-Cheng Liao, Chi-Wei Hsiao, Han-Yang Wang, Wei-Chen Chiu, Ching-Chun HuangAbstract
Blind Face Restoration aims to recover high-fidelity, detail-rich facial images from unknown degraded inputs, presenting significant challenges in preserving both identity and detail. Pre-trained diffusion models have been increasingly used as image priors to generate fine details. Still, existing methods often use fixed diffusion sampling timesteps and a global guidance scale, assuming uniform degradation. This limitation and potentially imperfect degradation kernel estimation frequently lead to under- or over-diffusion, resulting in an imbalance between fidelity and quality. We propose DynFaceRestore, a novel blind face restoration approach that learns to map any blindly degraded input to Gaussian blurry images. By leveraging these blurry images and their respective Gaussian kernels, we dynamically select the starting timesteps for each blurry image and apply closed-form guidance during the diffusion sampling process to maintain fidelity. Additionally, we introduce a dynamic guidance scaling adjuster that modulates the guidance strength across local regions, enhancing detail generation in complex areas while preserving structural fidelity in contours. This strategy effectively balances the trade-off between fidelity and quality. DynFaceRestore achieves state-of-the-art performance in both quantitative and qualitative evaluations, demonstrating robustness and effectiveness in blind face restoration.
Abstract (translated)
盲脸恢复的目标是从未知退化的输入中恢复高质量、细节丰富的面部图像，这在保持身份和细节的同时面临着重大挑战。预训练的扩散模型已经被越来越多地用作生成精细细节的图像先验。然而，现有的方法通常使用固定的扩散采样时间步长和全局指导尺度，假设退化是均匀的。这种限制以及可能不完美的退化核估计往往导致过度或不足的扩散，从而在保真度和质量之间造成不平衡。 我们提出了一种名为DynFaceRestore的新盲脸恢复方法，该方法能够将任何未知退化的输入映射到高斯模糊图像上。通过利用这些模糊图像及其相应的高斯核，我们可以为每个模糊图像动态选择起始时间步，并在扩散采样过程中应用闭式形式的指导来维持保真度。此外，我们引入了一个动态指导强度调节器，它可以跨局部区域调整引导强度，在复杂区域增强细节生成的同时保持轮廓中的结构保真度。这种策略有效地平衡了保真度和质量之间的权衡。 DynFaceRestore在定量和定性评估中均取得了最先进的性能，展示了其在盲脸恢复任务中的鲁棒性和有效性。
URL
https://arxiv.org/abs/2507.13797
PDF
-
Augmented Reality in Cultural Heritage: A Dual-Model Pipeline for 3D Artwork Reconstruction
2025-07-18 07:59:29Daniele Pannone, Alessia Castronovo, Maurizio Mancini, Gian Luca Foresti, Claudio Piciarelli, Rossana Gabrieli, Muhammad Yasir Bilal, Danilo AvolaAbstract
This paper presents an innovative augmented reality pipeline tailored for museum environments, aimed at recognizing artworks and generating accurate 3D models from single images. By integrating two complementary pre-trained depth estimation models, i.e., GLPN for capturing global scene structure and Depth-Anything for detailed local reconstruction, the proposed approach produces optimized depth maps that effectively represent complex artistic features. These maps are then converted into high-quality point clouds and meshes, enabling the creation of immersive AR experiences. The methodology leverages state-of-the-art neural network architectures and advanced computer vision techniques to overcome challenges posed by irregular contours and variable textures in artworks. Experimental results demonstrate significant improvements in reconstruction accuracy and visual realism, making the system a highly robust tool for museums seeking to enhance visitor engagement through interactive digital content.
Abstract (translated)
本文提出了一种创新的增强现实（AR）处理流程，专门针对博物馆环境设计，旨在识别艺术品并从单张图像中生成准确的3D模型。通过结合两个互补的预训练深度估计模型——GLPN 用于捕捉全局场景结构和Depth-Anything 用于详细局部重建——所提出的方案能够产生优化的深度图，这些图表有效地代表了复杂的艺术特征。随后，这些地图被转换为高质量的点云和网格，从而可以创建沉浸式的AR体验。 该方法利用最先进的神经网络架构和高级计算机视觉技术来克服由艺术品不规则轮廓和可变纹理带来的挑战。实验结果表明，在重建精度和视觉真实感方面取得了显著改善，使系统成为博物馆增强访客互动体验通过数字内容所需的强大工具。
URL
https://arxiv.org/abs/2507.13719
PDF
-
Unified Medical Image Segmentation with State Space Modeling Snake
2025-07-17 03:32:32Ruicheng Zhang, Haowei Guo, Kanghui Tian, Jun Zhou, Mingliang Yan, Zeyu Zhang, Shen ZhaoAbstract
Unified Medical Image Segmentation (UMIS) is critical for comprehensive anatomical assessment but faces challenges due to multi-scale structural heterogeneity. Conventional pixel-based approaches, lacking object-level anatomical insight and inter-organ relational modeling, struggle with morphological complexity and feature conflicts, limiting their efficacy in UMIS. We propose Mamba Snake, a novel deep snake framework enhanced by state space modeling for UMIS. Mamba Snake frames multi-contour evolution as a hierarchical state space atlas, effectively modeling macroscopic inter-organ topological relationships and microscopic contour refinements. We introduce a snake-specific vision state space module, the Mamba Evolution Block (MEB), which leverages effective spatiotemporal information aggregation for adaptive refinement of complex morphologies. Energy map shape priors further ensure robust long-range contour evolution in heterogeneous data. Additionally, a dual-classification synergy mechanism is incorporated to concurrently optimize detection and segmentation, mitigating under-segmentation of microstructures in UMIS. Extensive evaluations across five clinical datasets reveal Mamba Snake's superior performance, with an average Dice improvement of 3\% over state-of-the-art methods.
Abstract (translated)
统一医学图像分割（UMIS）对于全面的解剖评估至关重要，但由于多尺度结构异质性而面临挑战。传统基于像素的方法由于缺乏对象级别的解剖洞察力和器官间关系建模，在处理形态复杂性和特征冲突方面遇到困难，从而限制了其在UMIS中的有效性。我们提出了一种名为Mamba Snake的新颖深度蛇框架，该框架通过状态空间建模增强以用于UMIS。 Mamba Snake将多轮廓演变视为分层的状态空间图集（atlas），有效地建模宏观的器官间拓扑关系和微观的轮廓细化。我们引入了针对蛇特定视觉状态空间模块——Mamba Evolution Block (MEB)，该模块利用有效的时空信息聚合，以适应性地改进复杂形态的细化。 能量图形状先验进一步确保在异质数据中的稳健长程轮廓演化。此外，还集成了双分类协同机制，同时优化检测和分割，减少UMIS中微结构的欠分割现象。 通过对五个临床数据集进行广泛的评估，证明了Mamba Snake具有优越的表现力，在Dice分数上相较于最先进方法平均提高了3%。
URL
https://arxiv.org/abs/2507.12760
PDF
-
AortaDiff: Volume-Guided Conditional Diffusion Models for Multi-Branch Aortic Surface Generation
2025-07-17 00:36:51Delin An, Pan Du, Jian-Xun Wang, Chaoli WangAbstract
Accurate 3D aortic construction is crucial for clinical diagnosis, preoperative planning, and computational fluid dynamics (CFD) simulations, as it enables the estimation of critical hemodynamic parameters such as blood flow velocity, pressure distribution, and wall shear stress. Existing construction methods often rely on large annotated training datasets and extensive manual intervention. While the resulting meshes can serve for visualization purposes, they struggle to produce geometrically consistent, well-constructed surfaces suitable for downstream CFD analysis. To address these challenges, we introduce AortaDiff, a diffusion-based framework that generates smooth aortic surfaces directly from CT/MRI volumes. AortaDiff first employs a volume-guided conditional diffusion model (CDM) to iteratively generate aortic centerlines conditioned on volumetric medical images. Each centerline point is then automatically used as a prompt to extract the corresponding vessel contour, ensuring accurate boundary delineation. Finally, the extracted contours are fitted into a smooth 3D surface, yielding a continuous, CFD-compatible mesh representation. AortaDiff offers distinct advantages over existing methods, including an end-to-end workflow, minimal dependency on large labeled datasets, and the ability to generate CFD-compatible aorta meshes with high geometric fidelity. Experimental results demonstrate that AortaDiff performs effectively even with limited training data, successfully constructing both normal and pathologically altered aorta meshes, including cases with aneurysms or coarctation. This capability enables the generation of high-quality visualizations and positions AortaDiff as a practical solution for cardiovascular research.
Abstract (translated)
精确的3D主动脉构建对于临床诊断、术前规划和计算流体动力学（CFD）模拟至关重要，因为它能够估计诸如血流速度、压力分布和血管剪切应力等关键血液动力学参数。现有的构建方法通常依赖于大量标注的数据集以及大量的手动干预。虽然由此产生的网格可以用于可视化目的，但它们在生成几何一致性良好且适合后续CFD分析的表面方面存在困难。 为了应对这些挑战，我们引入了AortaDiff，这是一个基于扩散框架的方法，可以直接从CT/MRI体积数据中生成平滑的主动脉表面。AortaDiff首先采用一种由体素引导的条件扩散模型（CDM），以迭代方式根据体积医学图像生成主动脉中心线。然后自动使用每个中心线点作为提示来提取相应的血管轮廓，确保边界界定准确。最后，将提取出的轮廓拟合为一个平滑的3D表面，从而产生连续且适合CFD分析的网格表示。 AortaDiff相对于现有方法具有明显优势，包括端到端的工作流程、对大规模标注数据集依赖性小以及能够生成几何精度高且与CFD兼容的主动脉网格。实验结果表明，即使在训练数据有限的情况下，AortaDiff也能有效地构建正常和病理改变（如动脉瘤或狭窄）的主动脉网格。这一能力使得高质量可视化得以实现，并将AortaDiff定位为心血管研究中的实用解决方案。
URL
https://arxiv.org/abs/2507.13404
PDF
-
A Learning Framework For Cooperative Collision Avoidance of UAV Swarms Leveraging Domain Knowledge
2025-07-15 02:09:53Shuangyao Huang, Haibo Zhang, Zhiyi HuangAbstract
This paper presents a multi-agent reinforcement learning (MARL) framework for cooperative collision avoidance of UAV swarms leveraging domain knowledge-driven reward. The reward is derived from knowledge in the domain of image processing, approximating contours on a two-dimensional field. By modeling obstacles as maxima on the field, collisions are inherently avoided as contours never go through peaks or intersect. Additionally, counters are smooth and energy-efficient. Our framework enables training with large swarm sizes as the agent interaction is minimized and the need for complex credit assignment schemes or observation sharing mechanisms in state-of-the-art MARL approaches are eliminated. Moreover, UAVs obtain the ability to adapt to complex environments where contours may be non-viable or non-existent through intensive training. Extensive experiments are conducted to evaluate the performances of our framework against state-of-the-art MARL algorithms.
Abstract (translated)
本文提出了一种多智能体强化学习（MARL）框架，用于无人机群的协作避碰问题，并通过领域知识驱动奖励来实现这一目标。该奖励机制基于图像处理领域的知识，在二维场地上近似轮廓线。通过将障碍物建模为场地上的最大值点，碰撞自然得以避免，因为轮廓线不会穿过峰值或相交。此外，这种方法生成的路径是平滑且节能的。 我们的框架能够支持大规模无人机群训练，因为它减少了智能体之间的相互作用，并消除了最先进的MARL方法中复杂的信用分配方案或状态共享机制的需求。另外，通过密集训练，无人机获得了在复杂环境中适应的能力，在这些环境中轮廓可能不可行或不存在。 我们进行了大量的实验来评估所提出框架相对于现有最佳MARL算法的性能。
URL
https://arxiv.org/abs/2507.10913
PDF
-
ProGait: A Multi-Purpose Video Dataset and Benchmark for Transfemoral Prosthesis Users
2025-07-14 12:40:57Xiangyu Yin, Boyuan Yang, Weichen Liu, Qiyao Xue, Abrar Alamri, Goeran Fiedler, Wei GaoAbstract
Prosthetic legs play a pivotal role in clinical rehabilitation, allowing individuals with lower-limb amputations the ability to regain mobility and improve their quality of life. Gait analysis is fundamental for optimizing prosthesis design and alignment, directly impacting the mobility and life quality of individuals with lower-limb amputations. Vision-based machine learning (ML) methods offer a scalable and non-invasive solution to gait analysis, but face challenges in correctly detecting and analyzing prosthesis, due to their unique appearances and new movement patterns. In this paper, we aim to bridge this gap by introducing a multi-purpose dataset, namely ProGait, to support multiple vision tasks including Video Object Segmentation, 2D Human Pose Estimation, and Gait Analysis (GA). ProGait provides 412 video clips from four above-knee amputees when testing multiple newly-fitted prosthetic legs through walking trials, and depicts the presence, contours, poses, and gait patterns of human subjects with transfemoral prosthetic legs. Alongside the dataset itself, we also present benchmark tasks and fine-tuned baseline models to illustrate the practical application and performance of the ProGait dataset. We compared our baseline models against pre-trained vision models, demonstrating improved generalizability when applying the ProGait dataset for prosthesis-specific tasks. Our code is available at this https URL and dataset at this https URL.
Abstract (translated)
假肢在临床康复中扮演着至关重要的角色，能够帮助下肢截肢者恢复行动能力，并提高其生活质量。步态分析对于优化假肢的设计和对准至关重要，直接关系到下肢截肢者的移动能力和生活品质。基于视觉的机器学习（ML）方法为步态分析提供了一种可扩展且非侵入性的解决方案，但由于假肢的独特外观及新的运动模式，这种方法在正确检测和分析假肢方面面临挑战。 本文旨在通过介绍一个多用途数据集——ProGait来填补这一空白，以支持包括视频对象分割、2D人体姿态估计以及步态分析（GA）在内的多种视觉任务。该数据集包含来自四名大腿截肢者在测试多款新装配的假肢时进行行走试验所拍摄的412段视频片段，并描绘了使用股骨上端假肢的人体对象的存在、轮廓、姿势及步态模式。 除了提供数据集本身之外，我们还介绍了基准任务和微调后的基线模型，以展示ProGait数据集的实际应用及其性能。我们将我们的基线模型与预训练的视觉模型进行了比较，结果显示在应用于特定假肢任务时，使用ProGait数据集可以提高泛化能力。 我们的代码可在[此链接](https://this_https_URL)获取，而数据集则可通过[此链接](https://this_https_URL)访问。
URL
https://arxiv.org/abs/2507.10223
PDF
-
Automatic Contouring of Spinal Vertebrae on X-Ray using a Novel Sandwich U-Net Architecture
2025-07-12 06:40:18Sunil Munthumoduku Krishna Murthy, Kumar Rajamani, Srividya Tirunellai Rajamani, Yupei Li, Qiyang Sun, Bjoern W. SchullerAbstract
In spinal vertebral mobility disease, accurately extracting and contouring vertebrae is essential for assessing mobility impairments and monitoring variations during flexion-extension movements. Precise vertebral contouring plays a crucial role in surgical planning; however, this process is traditionally performed manually by radiologists or surgeons, making it labour-intensive, time-consuming, and prone to human error. In particular, mobility disease analysis requires the individual contouring of each vertebra, which is both tedious and susceptible to inconsistencies. Automated methods provide a more efficient alternative, enabling vertebra identification, segmentation, and contouring with greater accuracy and reduced time consumption. In this study, we propose a novel U-Net variation designed to accurately segment thoracic vertebrae from anteroposterior view on X-Ray images. Our proposed approach, incorporating a ``sandwich" U-Net structure with dual activation functions, achieves a 4.1\% improvement in Dice score compared to the baseline U-Net model, enhancing segmentation accuracy while ensuring reliable vertebral contour extraction.
Abstract (translated)
在脊柱椎体活动性疾病中，准确提取和描绘椎骨对于评估运动障碍以及监测屈伸运动期间的变化至关重要。精确的椎骨轮廓绘制在手术规划中起着关键作用；然而，这一过程传统上是由放射科医生或外科医生手动完成的，这使得该过程既费力又耗时，并且容易出现人为错误。特别是，活动性疾病分析需要对每个椎骨进行单独描绘，这是一个既繁琐又易出错的过程。 自动化方法提供了一个更高效的替代方案，能够以更高的精度和减少的时间消耗来识别、分割并描绘椎骨。在这项研究中，我们提出了一种新型的U-Net变体，旨在从X光片上精确地对胸椎进行分割（采用前后位视角）。我们的方法引入了带有双重激活函数的“三明治”结构U-Net模型，在Dice分数指标上相比基础U-Net模型提高了4.1%，从而增强了分割精度并确保了可靠的椎骨轮廓提取。
URL
https://arxiv.org/abs/2507.09158
PDF
-
Identification of Violin Reduction via Contour Lines Classification
2025-07-10 13:23:15Phil\'emon Beghin, Anne-Emmanuelle Ceulemans, Fran\c{c}ois GlineurAbstract
The first violins appeared in late 16th-century Italy. Over the next 200 years, they spread across Europe and luthiers of various royal courts, eager to experiment with new techniques, created a highly diverse family of instruments. Around 1750, size standards were introduced to unify violin making for orchestras and conservatories. Instruments that fell between two standards were then reduced to a smaller size by luthiers. These reductions have an impact on several characteristics of violins, in particular on the contour lines, i.e. lines of constant altitude, which look more like a U for non reduced instruments and a V for reduced ones. While such differences are observed by experts, they have not been studied quantitatively. This paper presents a method for classifying violins as reduced or non-reduced based on their contour lines. We study a corpus of 25 instruments whose 3D geometric meshes were acquired via photogrammetry. For each instrument, we extract 10-20 contour lines regularly spaced every millimetre. Each line is fitted with a parabola-like curve (with an equation of the type y = alpha*abs(x)**beta) depending on two parameters, describing how open (beta) and how vertically stretched (alpha) the curve is. We compute additional features from those parameters, using regressions and counting how many values fall under some threshold. We also deal with outliers and non equal numbers of levels, and eventually obtain a numerical profile for each instrument. We then apply classification methods to assess whether geometry alone can predict size reduction. We find that distinguishing between reduced and non reduced instruments is feasible to some degree, taking into account that a whole spectrum of more or less transformed violins exists, for which it is more difficult to quantify the reduction. We also find the opening parameter beta to be the most predictive.
Abstract (translated)
第一把小提琴出现在16世纪晚期的意大利。在接下来的200年里，它们传播到了整个欧洲，各个宫廷里的制琴师们热衷于尝试新技术，从而创造出了一个高度多样化的乐器家族。大约到1750年，为使乐团和音乐学院中的小提琴制作标准化，制定了尺寸标准。那些介于两种标准之间的小提琴则被制琴师缩小尺寸。这些缩减影响了小提琴的多个特性，尤其是在轮廓线方面：对于未被缩减的小提琴而言，轮廓线看上去更像一个“U”形；而对于已被缩减的小提琴，则更像是一个“V”形。尽管专家们观察到了这样的差异，但这些变化尚未得到定量研究。 本文介绍了一种基于小提琴的轮廓线来分类其是否为缩减型的方法。我们研究了一个包含25把乐器的数据集，其中每把乐器的3D几何网格是通过摄影测量技术获得的。对于每个乐器，我们会提取出10-20条间隔一毫米等距分布的轮廓线，并使用一个类似抛物线的曲线（方程形式为y = alpha * abs(x)**beta）来拟合每一根线条，这条曲线由两个参数描述，即开放程度(beta)和垂直拉伸度(alpha)。根据这些参数，我们计算出额外的特征值，包括回归分析以及统计哪些数值低于某个阈值的数量等，并处理异常值及不同数量级的问题，最终为每把乐器获得一个数值轮廓。之后，我们将应用分类方法来评估仅凭几何形状是否能够预测尺寸缩减。 我们的研究发现，在一定程度上可以区分出被缩减与未被缩减的小提琴，尽管考虑到存在一系列程度不同的变形小提琴，这种区分更加困难。此外，我们还发现开放性参数(beta)具有最强的预测能力。
URL
https://arxiv.org/abs/2507.07743
PDF
-
Objectomaly: Objectness-Aware Refinement for OoD Segmentation with Structural Consistency and Boundary Precision
2025-07-10 06:23:35Jeonghoon Song, Sunghun Kim, Jaegyun Im, Byeongjoon NohAbstract
Out-of-Distribution (OoD) segmentation is critical for safety-sensitive applications like autonomous driving. However, existing mask-based methods often suffer from boundary imprecision, inconsistent anomaly scores within objects, and false positives from background noise. We propose \textbf{\textit{Objectomaly}}, an objectness-aware refinement framework that incorporates object-level priors. Objectomaly consists of three stages: (1) Coarse Anomaly Scoring (CAS) using an existing OoD backbone, (2) Objectness-Aware Score Calibration (OASC) leveraging SAM-generated instance masks for object-level score normalization, and (3) Meticulous Boundary Precision (MBP) applying Laplacian filtering and Gaussian smoothing for contour refinement. Objectomaly achieves state-of-the-art performance on key OoD segmentation benchmarks, including SMIYC AnomalyTrack/ObstacleTrack and RoadAnomaly, improving both pixel-level (AuPRC up to 96.99, FPR$_{95}$ down to 0.07) and component-level (F1$-$score up to 83.44) metrics. Ablation studies and qualitative results on real-world driving videos further validate the robustness and generalizability of our method. Code will be released upon publication.
Abstract (translated)
**翻译** 分布外（OoD，Out-of-Distribution）分割对于自动驾驶等安全敏感型应用至关重要。然而，现有的基于掩码的方法常常会遇到边界不精确、对象内部异常分数不一致以及背景噪声导致的假阳性的问题。为此，我们提出了**Objectomaly**——一个基于目标特性的改进框架，该框架利用了物体级别的先验知识。Objectomaly包括三个阶段：（1）粗略异常评分（CAS），使用现有的OoD骨干网络；（2）目标感知得分校准（OASC），通过SAM生成的实例掩码对对象级别的分数进行归一化处理；以及（3）细致边界精度（MBP），应用拉普拉斯滤波和高斯平滑以优化轮廓细节。在关键的OoD分割基准测试，如SMIYC AnomalyTrack/ObstacleTrack 和RoadAnomaly 上，Objectomaly实现了最先进的性能，在像素级别指标上取得了高达96.99的AuPRC值并把FPR$_{95}$降低到了0.07，并且在组件级别的F1-分数上达到了83.44。通过对实际驾驶视频中的消融研究和定性分析，进一步验证了我们方法的鲁棒性和泛化能力。代码将在发布后公开。
URL
https://arxiv.org/abs/2507.07460
PDF
-
Segmentation Regularized Training for Multi-Domain Deep Learning Registration applied to MR-Guided Prostate Cancer Radiotherapy
2025-07-09 15:55:32Sudharsan Madhavan, Chengcheng Gui, Lando Bosma, Josiah Simeth, Jue Jiang, Nicolas Cote, Nima Hassan Rezaeian, Himanshu Nagar, Victoria Brennan, Neelam Tyagi, Harini VeeraraghavanAbstract
Background: Accurate deformable image registration (DIR) is required for contour propagation and dose accumulation in MR-guided adaptive radiotherapy (MRgART). This study trained and evaluated a deep learning DIR method for domain invariant MR-MR registration. Methods: A progressively refined registration and segmentation (ProRSeg) method was trained with 262 pairs of 3T MR simulation scans from prostate cancer patients using weighted segmentation consistency loss. ProRSeg was tested on same- (58 pairs), cross- (72 1.5T MR Linac pairs), and mixed-domain (42 MRSim-MRL pairs) datasets for contour propagation accuracy of clinical target volume (CTV), bladder, and rectum. Dose accumulation was performed for 42 patients undergoing 5-fraction MRgART. Results: ProRSeg demonstrated generalization for bladder with similar Dice Similarity Coefficients across domains (0.88, 0.87, 0.86). For rectum and CTV, performance was domain-dependent with higher accuracy on cross-domain MRL dataset (DSCs 0.89) versus same-domain data. The model's strong cross-domain performance prompted us to study the feasibility of using it for dose accumulation. Dose accumulation showed 83.3% of patients met CTV coverage (D95 >= 40.0 Gy) and bladder sparing (D50 <= 20.0 Gy) constraints. All patients achieved minimum mean target dose (>40.4 Gy), but only 9.5% remained under upper limit (<42.0 Gy). Conclusions: ProRSeg showed reasonable multi-domain MR-MR registration performance for prostate cancer patients with preliminary feasibility for evaluating treatment compliance to clinical constraints.
Abstract (translated)
背景：在磁共振引导的自适应放射治疗（MRgART）中，准确的可变形图像配准（DIR）对于轮廓传播和剂量积累是必需的。本研究训练并评估了一种用于领域不变的MRI-MRI注册的深度学习DIR方法。 方法：通过使用加权分割一致性损失，在262对前列腺癌患者的3T MR模拟扫描上训练了逐步细化的注册与分割（ProRSeg）方法。该方法在相同域（58对）、跨域（72个1.5T MR Linac对）和混合域（42个MRSim-MRL对）的数据集上进行了测试，评估临床靶区体积（CTV）、膀胱和直肠轮廓传播的准确性。对于接受5次分割MRgART治疗的42名患者进行了剂量积累。 结果：ProRSeg在不同领域中展示了良好的泛化性能，尤其是在膀胱的Dice相似系数方面，在各个域内均保持稳定（分别为0.88、0.87和0.86）。对于直肠和CTV而言，其表现依赖于域别，跨域MRL数据集上的准确性更高（DSCs为0.89）与同一领域的数据相比。模型的强跨领域性能促使我们研究使用该模型进行剂量积累的可行性。在42名患者中，有83.3%的人满足CTV覆盖（D95 >= 40.0 Gy）和膀胱保护（D50 <= 20.0 Gy）的约束条件。所有患者均达到了最低平均靶区剂量（>40.4 Gy），但只有9.5%的患者低于上限（<42.0 Gy）。 结论：对于前列腺癌患者，ProRSeg在多领域MRI-MRI配准方面展示了合理的性能，并初步证明了其用于评估治疗是否符合临床限制条件的可能性。
URL
https://arxiv.org/abs/2507.06966
PDF
-
Knowledge-guided Complex Diffusion Model for PolSAR Image Classification in Contourlet Domain
2025-07-08 04:50:28Junfei Shi, Yu Cheng, Haiyan Jin, Junhuai Li, Zhaolin Xiao, Maoguo Gong, Weisi LinAbstract
Diffusion models have demonstrated exceptional performance across various domains due to their ability to model and generate complicated data distributions. However, when applied to PolSAR data, traditional real-valued diffusion models face challenges in capturing complex-valued phase this http URL, these models often struggle to preserve fine structural details. To address these limitations, we leverage the Contourlet transform, which provides rich multiscale and multidirectional representations well-suited for PolSAR imagery. We propose a structural knowledge-guided complex diffusion model for PolSAR image classification in the Contourlet domain. Specifically, the complex Contourlet transform is first applied to decompose the data into low- and high-frequency subbands, enabling the extraction of statistical and boundary features. A knowledge-guided complex diffusion network is then designed to model the statistical properties of the low-frequency components. During the process, structural information from high-frequency coefficients is utilized to guide the diffusion process, improving edge preservation. Furthermore, multiscale and multidirectional high-frequency features are jointly learned to further boost classification accuracy. Experimental results on three real-world PolSAR datasets demonstrate that our approach surpasses state-of-the-art methods, particularly in preserving edge details and maintaining region homogeneity in complex terrain.
Abstract (translated)
扩散模型由于能够建模和生成复杂的数据分布，在多个领域内展示了卓越的性能。然而，当应用于极化合成孔径雷达（PolSAR）数据时，传统的实数值扩散模型在捕捉复杂的相位信息方面遇到挑战，并且难以保留精细的结构细节。为了解决这些问题，我们利用了轮廓波变换（Contourlet transform），该技术提供了丰富的多尺度和多方向表示，特别适合用于极化合成孔径雷达图像处理。 为此，我们提出了一种基于轮廓波域中的结构知识引导型复扩散模型，以提高PolSAR图像分类的准确性。具体而言，首先使用复数轮廓波变换将数据分解为低频和高频子带，从而能够提取统计特性和边界特征。接着设计了一个知识引导下的复扩散网络，用于建模低频分量的统计特性。在此过程中，利用高频系数中的结构信息来指导扩散过程，以提高边缘保留能力。此外，通过联合学习多尺度和多方向的高频特征进一步提升分类精度。 实验结果表明，在三个真实的PolSAR数据集上，我们的方法超越了现有最先进的技术，特别是在复杂地形中保持边界细节和区域同质性方面表现尤为突出。
URL
https://arxiv.org/abs/2507.05666
PDF
-
Fast-VGAN: Lightweight Voice Conversion with Explicit Control of F0 and Duration Parameters
2025-07-07 09:36:00Mathilde Abrassart, Nicolas Obin, Axel RoebelAbstract
Precise control over speech characteristics, such as pitch, duration, and speech rate, remains a significant challenge in the field of voice conversion. The ability to manipulate parameters like pitch and syllable rate is an important element for effective identity conversion, but can also be used independently for voice transformation, achieving goals that were historically addressed by vocoder-based methods. In this work, we explore a convolutional neural network-based approach that aims to provide means for modifying fundamental frequency (F0), phoneme sequences, intensity, and speaker identity. Rather than relying on disentanglement techniques, our model is explicitly conditioned on these factors to generate mel spectrograms, which are then converted into waveforms using a universal neural vocoder. Accordingly, during inference, F0 contours, phoneme sequences, and speaker embeddings can be freely adjusted, allowing for intuitively controlled voice transformations. We evaluate our approach on speaker conversion and expressive speech tasks using both perceptual and objective metrics. The results suggest that the proposed method offers substantial flexibility, while maintaining high intelligibility and speaker similarity.
Abstract (translated)
在语音转换领域，对音高、持续时间及语速等语音特征的精确控制仍然是一个重大挑战。操控音高和音节率这类参数的能力是有效身份转换的重要元素，但也可以独立使用这些参数进行声音变换，以实现以往基于声码器的方法才能达到的目标。本文提出了一种基于卷积神经网络的方法，旨在提供修改基频（F0）、音素序列、强度及说话人身份的手段。与依赖于特征解耦技术不同的是，我们的模型直接根据这些因素生成梅尔光谱图，并使用通用神经声码器将其转换为波形信号。因此，在推理过程中可以自由调整F0轮廓、音素序列和说话人嵌入，从而实现直观可控的声音变换。 我们在说话人转换及表情语音任务上采用感知与客观指标对我们的方法进行了评估。实验结果表明，所提出的方法在保持高清晰度和说话人口感相似性的前提下，提供了相当大的灵活性。
URL
https://arxiv.org/abs/2507.04817
PDF
-
VectorLLM: Human-like Extraction of Structured Building Contours vis Multimodal LLMs
2025-07-07 05:10:15Tao Zhang, Shiqing Wei, Shihao Chen, Wenling Yu, Muying Luo, Shunping JiAbstract
Automatically extracting vectorized building contours from remote sensing imagery is crucial for urban planning, population estimation, and disaster assessment. Current state-of-the-art methods rely on complex multi-stage pipelines involving pixel segmentation, vectorization, and polygon refinement, which limits their scalability and real-world applicability. Inspired by the remarkable reasoning capabilities of Large Language Models (LLMs), we introduce VectorLLM, the first Multi-modal Large Language Model (MLLM) designed for regular building contour extraction from remote sensing images. Unlike existing approaches, VectorLLM performs corner-point by corner-point regression of building contours directly, mimicking human annotators' labeling process. Our architecture consists of a vision foundation backbone, an MLP connector, and an LLM, enhanced with learnable position embeddings to improve spatial understanding capability. Through comprehensive exploration of training strategies including pretraining, supervised fine-tuning, and preference optimization across WHU, WHU-Mix, and CrowdAI datasets, VectorLLM significantly outperformed the previous SOTA methods by 5.6 AP, 7.1 AP, 13.6 AP, respectively in the three datasets. Remarkably, VectorLLM exhibits strong zero-shot performance on unseen objects including aircraft, water bodies, and oil tanks, highlighting its potential for unified modeling of diverse remote sensing object contour extraction tasks. Overall, this work establishes a new paradigm for vector extraction in remote sensing, leveraging the topological reasoning capabilities of LLMs to achieve both high accuracy and exceptional generalization. All the codes and weights will be published for promoting community development.
Abstract (translated)
从遥感影像中自动提取向量化的建筑轮廓对于城市规划、人口估算和灾害评估至关重要。当前最先进的方法依赖于复杂的多阶段流水线，包括像素分割、向量化和多边形优化，这限制了它们的可扩展性和实际应用性。受大型语言模型（LLM）卓越推理能力的启发，我们介绍了VectorLLM，这是首个专为从遥感图像中提取规则建筑轮廓而设计的多模态大型语言模型（MLLM）。与现有方法不同的是，VectorLLM直接进行逐角点回归以生成建筑轮廓，模仿人类标注者的标注过程。我们的架构包括视觉基础骨干网络、MLP连接器和一个增强了可学习位置嵌入的LLM，从而提高了空间理解能力。 通过全面探索包括预训练、监督微调和偏好优化在内的多种训练策略，VectorLLM在WHU、WHU-Mix和CrowdAI数据集上分别比之前的最先进方法（SOTA）高出5.6 AP、7.1 AP和13.6 AP的性能。值得注意的是，VectorLLM在包括飞机、水面和油罐在内的未见过物体上表现出强大的零样本性能，突显了其在统一建模各种遥感目标轮廓提取任务中的潜力。 总体而言，这项工作为遥感领域向量抽取建立了一种新的范式，通过利用大型语言模型的拓扑推理能力，在高精度的同时实现了出色的泛化效果。所有代码和权重将发布以促进社区发展。
URL
https://arxiv.org/abs/2507.04664
PDF
-
VLMs have Tunnel Vision: Evaluating Nonlocal Visual Reasoning in Leading VLMs
2025-07-04 23:15:52Shmuel Berman, Jia DengAbstract
Visual Language Models (VLMs) excel at complex visual tasks such as VQA and chart understanding, yet recent work suggests they struggle with simple perceptual tests. We present an evaluation that tests vision-language models' capacity for nonlocal visual reasoning -- reasoning that requires chaining evidence collected from multiple, possibly distant, regions of an image. We isolate three distinct forms of non-local vision: comparative perception, which demands holding two images in working memory and comparing them; saccadic search, which requires making discrete, evidence-driven jumps to locate successive targets; and smooth visual search, which involves searching smoothly along a continuous contour. Flagship models (e.g., Gemini 2.5 Pro, Claude Vision 3.7, GPT-o4-mini), even those that perform well on prior primitive-vision benchmarks, fail these tests and barely exceed random accuracy on two variants of our tasks that are trivial for humans. Our structured evaluation suite allows us to test if VLMs can perform similar visual algorithms to humans. Our findings show that despite gains in raw visual acuity, current models lack core visual reasoning capabilities.
Abstract (translated)
视觉语言模型（VLMs）在复杂视觉任务如视觉问答（VQA）和图表理解方面表现出色，但最近的研究表明它们在简单的感知测试中表现不佳。我们提出了一种评估方法，用于检验视觉-语言模型进行非局部视觉推理的能力——这种推理需要从图像中的多个、可能相距甚远的区域收集证据并将其串联起来。我们将非局部视觉分为三种不同的形式：比较感知（要求将两张图片保留在工作记忆中并进行对比），扫视搜索（需要根据证据做出离散跳跃以定位连续的目标），以及平滑视觉搜索（涉及沿着连续轮廓进行平滑搜索）。 即使是一些旗舰模型（如Gemini 2.5 Pro、Claude Vision 3.7 和 GPT-o4-mini），在先前的基础视觉基准测试中表现良好，但在我们设计的任务变体中也失败了。这些任务对人类来说是微不足道的，但模型的表现仅略高于随机猜测水平。 我们的结构化评估套件使我们能够检验VLM是否可以执行与人类相似的视觉算法。研究结果表明，尽管在基本视觉敏锐度方面有所提升，目前的模型仍然缺乏核心的视觉推理能力。
URL
https://arxiv.org/abs/2507.13361
PDF
-
Foundation versus Domain-specific Models: Performance Comparison, Fusion, and Explainability in Face Recognition
2025-07-04 12:46:45Redwan Sony, Parisa Farmanifard, Arun Ross, Anil K. JainAbstract
In this paper, we address the following question: How do generic foundation models (e.g., CLIP, BLIP, LLaVa, DINO) compare against a domain-specific face recognition model (viz., AdaFace or ArcFace) on the face recognition task? Through a series of experiments involving several foundation models and benchmark datasets, we are able to report the following findings: (a) In all datasets considered, domain-specific models outperformed zero-shot foundation models. (b) The performance of zero-shot generic foundation models improves on over-segmented face images than tightly cropped faces thereby suggesting the importance of contextual clues. For example, at a False Match Rate (FMR) of 0.01%, the True Match Rate (TMR) of OpenCLIP improved from 64.97% to 81.73% on the LFW dataset as the face crop increased from 112x112 to 250x250 while the TMR of domain-specific AdaFace dropped from 99.09% to 77.31%. (c) A simple score-level fusion of a foundation model with a domain-specific FR model improved the accuracy at low FMRs. For example, the TMR of AdaFace when fused with BLIP improved from 72.64% to 83.31% at an FMR of 0.0001% on the IJB-B dataset and from 73.17% to 85.81% on the IJB-C dataset. (d) Foundation models, such as ChatGPT, can be used to impart explainability to the FR pipeline (e.g., ``Despite minor lighting and head tilt differences, the two left-profile images show high consistency in forehead slope, nose shape, chin contour...''). In some instances, foundation models are even able to resolve low-confidence decisions made by AdaFace (e.g., ``Although AdaFace assigns a low similarity score of 0.21, both images exhibit visual similarity...and the pair is likely of the same person''), thereby reiterating the importance of combining domain-specific FR models with generic foundation models in a judicious manner.
Abstract (translated)
在这篇论文中，我们探讨了以下问题：通用基础模型（如CLIP、BLIP、LLaVa、DINO）与专用于人脸识别的领域特定模型（例如AdaFace或ArcFace）在人脸识别任务上的表现如何？通过一系列涉及多个基础模型和基准数据集的实验，我们得出了如下发现： (a) 在所有考虑的数据集中，领域特定模型的表现优于零样本基础模型。 (b) 零样本通用基础模型在处理过度分割的人脸图像时比紧密裁剪的人脸图像表现出更好的性能，这表明上下文线索的重要性。例如，在错误匹配率为0.01%的情况下，OpenCLIP在LFW数据集上的真匹配率从64.97%提升到了81.73%，当面部裁剪尺寸由112x112增加到250x250时；相比之下，领域特定的AdaFace模型的真匹配率却从99.09%下降到了77.31%。 (c) 将基础模型与专有的人脸识别模型进行简单的分数级融合可以提高低错误匹配率下的准确性。例如，在IJB-B数据集上，当AdaFace与BLIP融合后，以0.0001%的FMR计算时，真匹配率从72.64%提升到了83.31%，而在IJB-C数据集上的真匹配率则从73.17%提高到85.81%。 (d) 像ChatGPT这样的基础模型可以用于为人脸识别管道赋予解释性（例如，“尽管光线和头部角度略有不同，两张侧面照在前额斜度、鼻形和下巴轮廓方面表现出高度一致性……”）。在某些情况下，基础模型甚至能够解决AdaFace做出的低置信度决策（例如，“虽然AdaFace给出的相似分数为0.21较低，但两幅图像具有视觉上的相似性……这对可能是同一个人的照片。”），这进一步强调了以明智的方式结合领域特定的人脸识别模型与通用基础模型的重要性。
URL
https://arxiv.org/abs/2507.03541
PDF
-
TABNet: A Triplet Augmentation Self-Recovery Framework with Boundary-Aware Pseudo-Labels for Medical Image Segmentation
2025-07-03 07:50:00Peilin Zhang, Shaouxan Wua, Jun Feng, Zhuo Jin, Zhizezhang Gao, Jingkun Chen, Yaqiong Xing, Xiao ZhangAbstract
Background and objective: Medical image segmentation is a core task in various clinical applications. However, acquiring large-scale, fully annotated medical image datasets is both time-consuming and costly. Scribble annotations, as a form of sparse labeling, provide an efficient and cost-effective alternative for medical image segmentation. However, the sparsity of scribble annotations limits the feature learning of the target region and lacks sufficient boundary supervision, which poses significant challenges for training segmentation networks. Methods: We propose TAB Net, a novel weakly-supervised medical image segmentation framework, consisting of two key components: the triplet augmentation self-recovery (TAS) module and the boundary-aware pseudo-label supervision (BAP) module. The TAS module enhances feature learning through three complementary augmentation strategies: intensity transformation improves the model's sensitivity to texture and contrast variations, cutout forces the network to capture local anatomical structures by masking key regions, and jigsaw augmentation strengthens the modeling of global anatomical layout by disrupting spatial continuity. By guiding the network to recover complete masks from diverse augmented inputs, TAS promotes a deeper semantic understanding of medical images under sparse supervision. The BAP module enhances pseudo-supervision accuracy and boundary modeling by fusing dual-branch predictions into a loss-weighted pseudo-label and introducing a boundary-aware loss for fine-grained contour refinement. Results: Experimental evaluations on two public datasets, ACDC and MSCMR seg, demonstrate that TAB Net significantly outperforms state-of-the-art methods for scribble-based weakly supervised segmentation. Moreover, it achieves performance comparable to that of fully supervised methods.
Abstract (translated)
背景和目标：医学图像分割是临床应用中的核心任务之一。然而，获取大规模、全面标注的医学影像数据集既耗时又昂贵。草图注解作为一种稀疏标签形式，为医学图像分割提供了一种高效且成本效益高的替代方案。但是，草图注解的稀疏性限制了目标区域的特征学习，并缺乏足够的边界监督，这给训练分割网络带来了重大挑战。 方法：我们提出了一种新型弱监督医学影像分割框架TAB Net，该框架包含两个关键组成部分：三元组增强自我恢复（TAS）模块和边界感知伪标签监督（BAP）模块。TAS模块通过三种互补的增强策略来提高特征学习能力：强度变换增强了模型对纹理和对比度变化的敏感性；裁剪操作迫使网络在遮盖关键区域的情况下捕捉局部解剖结构；拼图增广则通过破坏空间连续性来加强全局解剖布局的建模。TAS模块引导网络从多样化的增强输入中恢复完整的掩码，从而在稀疏监督下促进医学影像的语义理解。 BAP模块通过将双支路预测融合成一个加权伪标签，并引入边界感知损失进行细粒度轮廓精炼来提高伪监督准确性及边界建模。这种方法不仅提高了伪标签的质量，还增强了对图像边缘细节的关注和建模能力。 结果：在两个公开数据集ACDC和MSCMR seg上的实验评估表明，TAB Net显著优于基于草图的弱监督分割方法中的最新技术，并且其性能与全监督方法相当。
URL
https://arxiv.org/abs/2507.02399
PDF
-
ShapeEmbed: a self-supervised learning framework for 2D contour quantification
2025-07-01 17:55:57Anna Foix Romero, Craig Russell, Alexander Krull, Virginie UhlmannAbstract
The shape of objects is an important source of visual information in a wide range of applications. One of the core challenges of shape quantification is to ensure that the extracted measurements remain invariant to transformations that preserve an object's intrinsic geometry, such as changing its size, orientation, and position in the image. In this work, we introduce ShapeEmbed, a self-supervised representation learning framework designed to encode the contour of objects in 2D images, represented as a Euclidean distance matrix, into a shape descriptor that is invariant to translation, scaling, rotation, reflection, and point indexing. Our approach overcomes the limitations of traditional shape descriptors while improving upon existing state-of-the-art autoencoder-based approaches. We demonstrate that the descriptors learned by our framework outperform their competitors in shape classification tasks on natural and biological images. We envision our approach to be of particular relevance to biological imaging applications.
Abstract (translated)
物体的形状是许多应用中重要的视觉信息来源。量化形状的一个核心挑战在于确保提取出的测量值在保持对象固有几何不变的情况下（如改变其大小、方向和图像中的位置）仍然具有不变性。在这项工作中，我们介绍了ShapeEmbed，这是一个自我监督表示学习框架，旨在将二维图像中物体轮廓（以欧几里得距离矩阵的形式表示）编码为一种形状描述符，这种描述符在平移、缩放、旋转、反射和平点索引下保持不变。我们的方法克服了传统形状描述符的局限性，并且改进了现有的基于自编码器的最佳实践。我们展示了通过我们框架学习到的描述符在自然图像和生物图像中的形状分类任务上优于其竞争对手的表现。我们认为，我们的方法特别适用于生物成像应用。
URL
https://arxiv.org/abs/2507.01009
PDF
-
Automated Workflow for the Detection of Vugs
2025-07-01 14:03:02M. Quamer Nasim, T. Maiti, N. Mosavat, P. V. Grech, T. Singh, P. Nath Singha RoyAbstract
Image logs are crucial in capturing high-quality geological information about subsurface formations. Among the various geological features that can be gleaned from Formation Micro Imager log, vugs are essential for reservoir evaluation. This paper introduces an automated Vug Detection Model, leveraging advanced computer vision techniques to streamline the vug identification process. Manual and semiautomated methods are limited by individual bias, labour-intensity and inflexibility in parameter finetuning. Our methodology also introduces statistical analysis on vug characteristics. Pre-processing steps, including logical file extraction and normalization, ensured standardized and usable data. The sixstep vug identification methodology encompasses top-k mode extraction, adaptive thresholding, contour identification, aggregation, advanced filtering, and optional filtering for low vuggy regions. The model's adaptability is evidenced by its ability to identify vugs missed by manual picking undertaken by experts. Results demonstrate the model's accuracy through validation against expert picks. Detailed metrics, such as count, mean, and standard deviation of vug areas within zones, were introduced, showcasing the model's capabilities compared to manual picking. The vug area distribution plot enhances understanding of vug types in the reservoir. This research focuses on the identification and characterization of vugs that in turn aids in the better understanding of reservoirs.
Abstract (translated)
图像日志在捕捉地下地层的高质量地质信息方面至关重要。在从岩性微成像测井中获取的各种地质特征中，孔穴（vugs）对于储层评价尤为关键。本文介绍了一种自动化的孔穴检测模型，该模型利用先进的计算机视觉技术来简化孔穴识别过程。手动和半自动方法受限于个体偏差、劳动强度以及参数微调的不灵活性。我们的研究方法还引入了对孔穴特征进行统计分析的方法。在预处理步骤中，包括逻辑文件提取和归一化等措施确保数据标准化且可使用。六步孔穴识别方法涵盖了top-k模式提取、自适应阈值设定、轮廓识别、聚类、高级过滤以及针对低孔隙区的可选过滤。该模型的适应性体现在其能够发现专家手动挑选过程中遗漏的孔穴，这一点通过与专家选择的结果进行对比验证了模型的准确性。详细度量指标包括各区域内的孔穴数量、平均面积和标准差等数据被引入，展示了模型相较于手工操作的能力。孔穴分布图有助于更深入地理解储层中的不同类型的孔穴。 这项研究专注于识别和表征孔穴，从而更好地了解储层特性。
URL
https://arxiv.org/abs/2507.02988
PDF
