Towards improved video super resolution for real-world applications ; master's thesis in artificial intelligence
other
Video or, Multi Frame, Super Resolution (VSR or, MFSR) techniques aim to generate high-resolution frame reconstructions of corresponding low-resolution ones. These techniques differ from the Single Image or, Frame, Super Resolution (SISR or, SFSR) ones in that they can additionally exploit the temporal nature of the input data. The advantage of having additional temporal information does not translate directly into an easier problem to solve. The challenge lies in the optimal extraction of this additional information. Current state-of-the-art methods are still using some variants of optical flow estimation plus warping for extraction and integration of temporal information but it is well known that during the warping process a lot of the high frequency information get lost. We investigated alternative architectures to alleviate or
suppress this problem but they only perform on par or slightly worst than current SOTA networks.
suppress this problem but they only perform on par or slightly worst than current SOTA networks.
TNO Identifier
878486
Publisher
Radboud University Artificial Cognitive Systems group, Department of Artificial Intelligence
Collation
50 p.
Place of publication
Nijmegen