Detail-revealing Deep Video Super-resolution
Previous CNN-based video super-resolution approaches need to align multiple frames to the reference. In this paper, we show that proper frame alignment and motion compensation is crucial for achieving high quality results. We accordingly propose a `sub-pixel motion compensation' (SPMC) layer in a CNN framework. Analysis and experiments show the suitability of this layer in video SR. The final end-to-end, scalable CNN framework effectively incorporates the SPMC layer and fuses multiple frames to reveal image details. Our implementation can generate visually and quantitatively high-quality results, superior to current state-of-the-arts, without the need of parameter tuning.
PDF Abstract ICCV 2017 PDF ICCV 2017 AbstractCode
Results from the Paper
Ranked #12 on Video Super-Resolution on MSU Video Upscalers: Quality Enhancement (VMAF metric)