Super-Resolving Compressed Video with Large Artifacts
Wenyi Zhao · 2015
We propose methods to super-resolve compressed video se-quences that may consist of frames with missing blocks of pixels in addition to compression artifacts. Different from traditional resolution enhancement algorithms, our meth-ods include two key components that are crucial to handle compressed video sequences. The first component is dy-namic masking that dynamically computes image masks used to reject outliers. The second component is flow-based image repairing that reconstructs missing blocks or a whole frame by exploring both temporal and spatial in-formation. We demonstrate the proposed methods with real MPEG video sequences. 1