Quadratic Video Interpolation for VTSR Challenge
Siyao Li, Xiangyu Xu, Ze Pan, Wenxiu Sun · 2019
Video interpolation is an important problem in image manipulation, which has drawn increased interests from the vision and graphics communities. In this work, we apply the quadratic video interpolation algorithm to the VTSR challenge of Advances in Image Manipulation (AIM) 2019, and introduce a joint finetuning scheme to exploit more training data. We provide a concise description of the quadratic model and present a detailed analysis of the results in the VTSR challenge. Extensive experiments demonstrate that our network generates high-quality interpolation results and outperforms the state-of-the-arts by a large margin.