ABSTRACTSuper-resolution localization microscopy allows visualization of biological structure at nanoscale resolution. However, the presence of heterogeneous background can degrade the nanoscale resolution by tens of nanometers and introduce significant image artifacts. Here we develop a new approach, referred to as extreme value based emitter recovery (EVER), to accurately recover the distorted fluorescent emitters from heterogeneous background. Through numerical simulation and biological experiments, we demonstrate that EVER significantly improves the accuracy and fidelity of the reconstructed super-resolution image for a wide variety of imaging characteristics. EVER requires no manual adjustment of parameters and is implemented as an easy-to-use ImageJ plugin that can immediately enhance the quality of super-resolution images. Our method paves the way for accurate nanoscale imaging of samples with heterogeneous background fluorescence, such as thicker tissue and cells.