Video super-resolution via pre-frame constrained and deep-feature enhanced sparse reconstruction
作者：
Highlights：
• A novel sparse reconstruction formulation is introduced for video super-resolution, which uses the previous estimated high-resolution frame as regularization to guarantee the temporal coherence.
• Deep features are incorporated into the sparse reconstruction framework to enhance the dictionary which benefit the whole super-resolution process.
• An effective dictionary updating strategy is proposed that updates the dictionaries regularly utilizing the newly reconstructed frames.
• A joint bilateral filter is utilized to remove reconstruction noises and transfer details.
• Experiments show the effectiveness of the proposed method compared with previous approaches.
摘要
•A novel sparse reconstruction formulation is introduced for video super-resolution, which uses the previous estimated high-resolution frame as regularization to guarantee the temporal coherence.•Deep features are incorporated into the sparse reconstruction framework to enhance the dictionary which benefit the whole super-resolution process.•An effective dictionary updating strategy is proposed that updates the dictionaries regularly utilizing the newly reconstructed frames.•A joint bilateral filter is utilized to remove reconstruction noises and transfer details.•Experiments show the effectiveness of the proposed method compared with previous approaches.
论文关键词：Video super resolution,Sparse representation,Deep features,Temporal coherence
论文评审过程：Received 30 May 2019, Revised 29 October 2019, Accepted 27 November 2019, Available online 27 November 2019, Version of Record 5 December 2019.
论文官网地址：https://doi.org/10.1016/j.patcog.2019.107139
