Reciprocal Attention Mixing Transformer for Lightweight Image Restoration

arXiv:2305.11474v4 Announce Type: replace
Abstract: Although many recent works have made advancements in the image restoration (IR) field, they often suffer from an excessive number of parameters. Another issue is that most Transformer-based IR methods focus only on either local or global features, leading to limited receptive fields or deficient parameter issues. To address these problems, we propose a lightweight IR network, Reciprocal Attention Mixing Transformer (RAMiT). It employs our proposed dimensional reciprocal attention mixing Transformer (D-RAMiT) blocks, which compute …

arxiv attention cs.ai cs.cv image image restoration restoration transformer type