Abstract: A method and an apparatus for determining near field images for optical lithography include receiving a thin mask image indicative of a photomask feature, in which the thin mask image is determined without considering a mask topography effect associated with the photomask feature, and determining a near field image from the thin mask image by a processor using an artificial neural network (ANN), in which the ANN uses the thin mask image as input. The apparatus includes a processor and a memory coupled to the processor. The memory configured to store instructions executed by the processor to perform the method.

Abstract: A method, an apparatus, and a non-transitory computer readable medium for full chip mask pattern generation include: generating, by a processor, an initial mask image from target polygons, performing, by the processor, a global image based full chip optimization of the initial mask image to generate new mask pattern polygons, wherein the global image based full chip optimization co-optimizes main feature polygons and SRAF image pixels, determining performance index information based on the global image based full chip optimization, wherein the performance index information comprises data for assisting a global polygon optimization, generating a mask based on the global polygon optimization of the new mask pattern polygons using the performance index information, and generating optimized mask patterns based on a localized polygon optimization of the mask.