IPT-V2: Efficient Image Processing Transformer using Hierarchical Attentions

arXiv:2404.00633v1 Announce Type: new
Abstract: Recent advances have demonstrated the powerful capability of transformer architecture in image restoration. However, our analysis indicates that existing transformerbased methods can not establish both exact global and local dependencies simultaneously, which are much critical to restore the details and missing content of degraded images. To this end, we present an efficient image processing transformer architecture with hierarchical attentions, called IPTV2, adopting a focal context self-attention (FCSA) and a global grid self-attention (GGSA) to obtain …

abstract advances analysis architecture arxiv capability cs.cv dependencies global hierarchical however image image processing image restoration images processing restore transformer transformer architecture type