发表机构
Beijing National Research Center for Information Science and Technology; Department of Electronic Engineering, Tsinghua University（北京信息科学与技术国家研究中心; 清华大学电子工程系）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
FPicker提出拓扑引导的开放曲线演化框架，通过中心-端点表示解决低信噪比显微图像中的丝状结构追踪问题，显著提升精度并降低拓扑断裂，在模拟和真实数据上均达最优性能。
AI 中文摘要
在冷冻电子显微镜（Cryo-EM）中，自动化丝状结构追踪对于三维螺旋重建至关重要，但面临交叉拓扑和极低信噪比（$\text{SNR} = \sigma_s^2/\sigma_n^2$ < 0.1 或 -10 dB）的挑战。现有范式均告失败：像素级分割器遭受严重的拓扑断裂，基于框的检测器面临幽灵中心漂移，顺序追踪器因误差累积而偏离轨道，传统活动轮廓在人为闭合曲线约束下崩溃。为解决这些瓶颈，我们提出FPicker，这是首个调和这些不兼容性的拓扑引导框架。它通过中心-端点表示和开放曲线演化模块统一感知，显式建模非循环连通性。在模拟基准上，FPicker在平均空间-角度精度（mSAP）上相对顶级基线提升超过40%，并在极端噪声（-20 dB）下将拓扑间隙率降低超过60%。通过学习内在物理几何而非局部纹理，FPicker展现出作为弹性几何骨干的强劲潜力。其在真实世界EMPIAR数据集上的零样本性能表现出稳健的拓扑抗性，微调后达到最先进的82.9% mSAP。我们的结果还表明，建模物理先验是弥合信号匮乏科学成像中模拟到现实差距的高度稳健路径。代码公开于：此 https URL。
英文摘要
Automating filament tracing in Cryo-Electron Microscopy (Cryo-EM) is essential for 3D helical reconstruction but challenged by intersecting topologies and extremely low Signal-to-Noise Ratios ($\text{SNR} = σ_s^2/σ_n^2$ < 0.1 or -10 dB). Existing paradigms fail: pixel-wise segmenters suffer from severe topological fracturing, box-based detectors face ghost center drift, sequential trackers derail due to error accumulation, and traditional active contours collapse under artificial closed-curve constraints. To resolve these bottlenecks, we present FPicker, the first topology-guided framework reconciling these incompatibilities. It unifies perception via a center-endpoint representation and an open-curve evolution module to explicitly model non-cyclic connectivity. On simulated benchmarks, FPicker outperforms top baselines by over $40\%$ relative gain in mean spatio-angular precision (mSAP) and reduces topological gap rates by over $60\%$ under extreme noise ($-20\text{ dB}$). By learning intrinsic physical geometry rather than local texture, FPicker demonstrates strong potential as a resilient geometric backbone. Its zero-shot performance on the real-world EMPIAR dataset exhibits robust topological resistance, achieving a state-of-the-art 82.9\% mSAP upon fine-tuning. Our results also suggest modeling physical priors is a highly robust path toward bridging the sim-to-real gap in signal-starved scientific imaging. The code is publicly available at: https://github.com/tomzhaosky/FPicker.
CommentsAccepted to the 19th European Conference on Computer Vision (ECCV 2026). 18 pages, 6 figures. Code is publicly available at: https://github.com/tomzhaosky/FPicker
Journal refComputer Vision - ECCV 2026. Lecture Notes in Computer Science, vol 17014. Springer, Cham
DOI：10.1007/978-3-032-37232-1_7
