Fix motion blur efficiently by sampling more in more blurred areas with Suin
Fix motion blur efficiently by sampling more in more blurred areas with Suin
Spatially-Attentive Patch-Hierarchical Network with Adaptive Sampling for Motion Deblurring
arXiv paper abstract https://arxiv.org/abs/2402.06117
arXiv PDF paper https://arxiv.org/pdf/2402.06117.pdf
This paper tackles the problem of motion deblurring of dynamic scenes.
Although end-to-end fully convolutional designs … advanced the state-of-the-art in non-uniform motion deblurring, their performance-complexity trade-off is still sub-optimal.
… propose a pixel adaptive and feature attentive design for handling large blur variations across different spatial locations and process each test image adaptively.
… design a content-aware global-local filtering … improves performance by considering not only global dependencies but also by dynamically exploiting neighboring pixel information.
… introduce a pixel-adaptive non-uniform sampling … implicitly discovers the difficult-to-restore regions … and … performs fine-grained refinement in a progressive manner.
… approach performs favorably against the state-of-the-art deblurring algorithms.
Stay up to date. Subscribe to my posts https://morrislee1234.wixsite.com/website/contact
Web site with my other posts by category https://morrislee1234.wixsite.com/website
LinkedIn https://www.linkedin.com/in/morris-lee-47877b7b
