Infrared (IR) images derived from cloudy skies are always too spatially varied for tiny targets to be detected, especially for single-frame detection. Using the neural networks (NN) nonlinear regression, discrimination, and self-leaning capability, an NN-based method is proposed for tiny point target detection in single-frame IR images with high background clutter. First, the background was estimated by an improved NN-based morphologic filter, the structure element of which was optimized by a two-layer NN. Second, noise characteristics were well studied, and thus a two-level segmentation is presented to delete noises as well as to further remove remaining background components. Last, images with several potential targets were fed to a BP NN that predicted the identity of the input, which was either a target or a pseudo-target. It is these two neural networks that separate target from background and pseudo-target, respectively, with different training destinations, thus avoiding the over-training problem. Results on real data indicate that, given the false alarm probability, the detection probability by this method reaches 98.3%, which is improved by 11.02% compared to the traditional approach with fixed SE and without trained NN.