Efficient Space-time Video Super Resolution using Low-Resolution Flow and Mask Upsampling
This work addresses the inefficiency and high computational cost of sequential video super-resolution and frame interpolation for video enhancement, offering a lightweight solution for applications like video editing and streaming.
The paper tackles the problem of generating high-resolution slow-motion videos from low-resolution, low-frame-rate inputs by proposing an efficient method that reuses flowmaps and masks from low-resolution interpolation, achieving better performance than state-of-the-art models on the REDS STSR Validation set.
This paper explores an efficient solution for Space-time Super-Resolution, aiming to generate High-resolution Slow-motion videos from Low Resolution and Low Frame rate videos. A simplistic solution is the sequential running of Video Super Resolution and Video Frame interpolation models. However, this type of solutions are memory inefficient, have high inference time, and could not make the proper use of space-time relation property. To this extent, we first interpolate in LR space using quadratic modeling. Input LR frames are super-resolved using a state-of-the-art Video Super-Resolution method. Flowmaps and blending mask which are used to synthesize LR interpolated frame is reused in HR space using bilinear upsampling. This leads to a coarse estimate of HR intermediate frame which often contains artifacts along motion boundaries. We use a refinement network to improve the quality of HR intermediate frame via residual learning. Our model is lightweight and performs better than current state-of-the-art models in REDS STSR Validation set.