Fast inverse lithography based on a model-driven block stacking convolutional neural network
This work addresses manufacturing challenges and cost issues in lithography for semiconductor production, representing an incremental improvement in OPC technology.
The paper tackles the problem of generating manufacturable photomasks for Optical Proximity Correction (OPC) in lithography by introducing a model-driven, block stacking convolutional neural network that speeds up mask generation and reduces reliance on labeled datasets, with numerical experiments confirming its effectiveness in managing mask complexity.
In the realm of lithography, Optical Proximity Correction (OPC) is a crucial resolution enhancement technique that optimizes the transmission function of photomasks on a pixel-based to effectively counter Optical Proximity Effects (OPE). However, conventional pixel-based OPC methods often generate patterns that pose manufacturing challenges, thereby leading to the increased cost in practical scenarios. This paper presents a novel inverse lithographic approach to OPC, employing a model-driven, block stacking deep learning framework that expedites the generation of masks conducive to manufacturing. This method is founded on vector lithography modelling and streamlines the training process by eliminating the requirement for extensive labeled datasets. Furthermore, diversity of mask patterns is enhanced by employing a wave function collapse algorithm, which facilitates the random generation of a multitude of target patterns, therefore significantly expanding the range of mask paradigm. Numerical experiments have substantiated the efficacy of the proposed end-to-end approach, highlighting its superior capability to manage mask complexity within the context of advanced OPC lithography. This advancement is anticipated to enhance the feasibility and economic viability of OPC technology within actual manufacturing environments.