Efficient Concertormer for Image Deblurring and Beyond

摘要

The Transformer architecture has excelled in NLP and vision tasks, but its self-attention complexity grows quadratically with image size, making high-resolution tasks computationally expensive. We introduce Concertormer, featuring Concerto Self-Attention (CSA) for image deblurring. CSA splits self-attention into global and local components while retaining partial information in additional dimensions, achieving linear complexity. A Cross-Dimensional Communication module enhances expressiveness by linearly combining attention maps. Additionally, our gated-dconv MLP merges the two-staged Transformer design into a single stage. Extensive evaluations show our method performs favorably against state-of-the-art works in deblurring, deraining, and JPEG artifact removal.