no code implementations • 9 Mar 2024 • Jingyun Xue, Tao Wang, Jun Wang, Kaihao Zhang, Wenhan Luo, Wenqi Ren, Zikun Liu, Hyunhee Park, Xiaochun Cao
Specifically, we utilize sparse self-attention to filter out redundant information and noise, directing the model's attention to focus on the features more relevant to the degraded regions in need of reconstruction.