Transcription of Dynamic Attentive Graph Learning for Image Restoration
{{id}} {{{paragraph}}}
Dynamic Attentive Graph Learning for Image RestorationChong Mou , Jian Zhang , , Zhuoyuan Wu Peking University Shenzhen Graduate School, Shenzhen, China Peng Cheng Laboratory, Shenzhen, self-similarity in natural images has been ver-ified to be an effective prior for Image Restoration . However,most existing deep non-local methods assign a fixed numberof neighbors for each query item, neglecting the dynamicsof non-local correlations. Moreover, the non-local correla-tions are usually based on pixels, prone to be biased due toimage degradation.
graph data, the main challenge of applying GCN to the image restoration community is how to construct a graph and perform graph convolution on regular grid data effec-tively. In this paper, we propose an improved graph atten-tion model to perform patch-wise graph convolution with dynamic graph connections for image restoration. The pro-
Domain:
Source:
Link to this page:
Please notify us if you found a problem with this document:
{{id}} {{{paragraph}}}