TBSN: Transformer-Based Blind-Spot Network for Self-Supervised Image Denoising

arXiv:2404.07846v1 Announce Type: new
Abstract: Blind-spot networks (BSN) have been prevalent network architectures in self-supervised image denoising (SSID). Existing BSNs are mostly conducted with convolution layers. Although transformers offer potential solutions to the limitations of convolutions and have demonstrated success in various image restoration tasks, their attention mechanisms may violate the blind-spot requirement, thus restricting their applicability in SSID. In this paper, we present a transformer-based blind-spot network (TBSN) by analyzing and redesigning the transformer operators that meet the blind-spot …

arxiv blind cs.cv denoising eess.iv image network spot transformer type