发表机构
The Chinese University of Hong Kong, Shenzhen; Shanghai Artificial Intelligence Laboratory（香港中文大学（深圳）; 上海人工智能实验室）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对不完整数据下的物理场重建，提出一种局部构建、全局修正的估计器，利用共享坐标条件预测器学习局部结构，并通过全域残差修正，在三个真实海洋数据集上MSE降低28.9%–34.5%。
AI 中文摘要
从总是包含缺失的训练样本中重建物理场，需要从碎片化的观测中学习空间结构。先前的工作确立了保留观测值如何提供有效的训练目标，但当每个训练场都不完整时，这并不能使完整场分布变得可识别。在有限数据下，关于尖锐过渡和局部变化的微弱证据可能进一步偏向于会削弱局部细节的平均预测。因此，需要一种结构先验来支持合理的补全；局部空间关系提供了一种基于此的先验。我们提出了一种局部构建、全局可修正的估计器，它显式地学习局部场估计，随后使用全域观测对其进行修正。一个共享的坐标条件预测器从不完整的补丁中学习，使得观测相对良好的邻域能够为局部结构提供直接监督。重叠的预测被协调成一个观测条件的共识场。一个全域估计器保留原始观测，并围绕这个冻结的场估计学习残差修正，使得局部构建的结构能够被更广泛的上下文所修正。局部估计既作为显式输入（连同其与观测的差异），也作为全局模型可以修改的预测起点。在三个具有真实观测间隙的真实海洋数据集上，我们的估计器在保留的源支持值上实现了最低的MSE和最高的PSNR，相对于最强外部基线将MSE降低了28.9%–34.5%。
英文摘要
Reconstructing physical fields from training samples that are always incomplete requires learning spatial structure from fragmented observations. Existing context--query work establishes how held-out observations provide valid training targets, but this does not make the complete-field distribution identifiable when every training field is incomplete. With finite data, weak evidence of sharp transitions and localized variations can further favor averaged predictions that attenuate local detail. A structural prior is therefore needed to favor plausible completions; local spatial relationships offer one grounded in the observations. We propose a locally constructed, globally revisable estimator that explicitly learns local field estimates and subsequently corrects them using full-domain observations. A shared coordinate-conditioned predictor learns from incomplete patches, allowing relatively well-observed neighborhoods to provide direct supervision of local structure. Its overlapping predictions are reconciled into an observation-conditioned consensus field. A full-domain estimator retains the original observations and learns a residual correction around this frozen field estimate, allowing locally constructed structure to be revised by broader evidence. The local estimate serves as both an explicit input, accompanied by its discrepancies with the observations, and a prediction starting point that the global model can revise. On three real-world ocean datasets with authentic observation gaps, our estimator achieves the lowest MSE and highest PSNR on withheld source-supported values, reducing MSE by 28.9%--34.5% against the strongest external baseline.
