Observation-Aligned Mask Priors for Learning Physical Dynamics from Authentic Occlusions

ArXi:2605.16818v1 Announce Type: new Learning physical dynamics directly from incomplete observations is challenging because authentic occlusions are structured, sample-dependent, and often missing not at random, whereas existing methods typically rely on heuristic masking rules or predefined mask distributions. We propose Observation-Aligned Mask Priors, a framework that learns the distribution of authentic observation masks and uses it to construct context-query partitions for