A Constrained Deformable Convolutional Network for Efficient Single Image Dynamic Scene Blind Deblurring with Spatially-Variant Motion Blur Kernels Estimation

Shu Tang, Yang Wu, Hongxing Qin +3

Most existing deep-learning-based single image dynamic scene blind deblurring (SIDSBD) methods usually design deep networks to directly remove the spatially-variant motion blurs fr…