Event-based Synthetic Aperture Imaging (E-SAI) extends the SAI technique to observe targets behind extremely dense occlusions. Existing approaches remain confined to the de-occlusion of a specific depth plane, i.e., single depth in focus, unable to be applied to observe occluded targets with varying depths due to the decreased focus range. To achieve All-in-Focus E-SAI, i.e., recovering the occlusion-free image of all depth planes, the depth information behind the occlusions should be given to ensure accurate event refocusing. In this paper, we first prove the feasibility of predicting the depth map from captured events in the presence of dense occlusions. Then, we propose the ESAI-AF network, which consists of a Depth Estimation Module (DEM) designed to estimate the depth information from multi-view events and an Image Enhancement Module (IEM) designed to reconstruct high-quality occlusion-free images from the refocused events. We employ only multi-view occlusion-free images as supervised signals for end-to-end training of the above modules. Extensive experiments have shown that the proposed method can effectively perform All-in-Focus image reconstruction of occluded multi-depth targets and achieves superior performance to existing methods.