“Human-centric video frame interpolation has great potential for improving people’s entertainment experiences and finding commercial applications in the sports analysis industry. … Although there are multiple benchmark datasets available in the community, none of them is dedicated for human-centric scenarios. To bridge this gap, we introduce SportsSloMo, a benchmark consisting of more than 130K video clips and 1M video frames of high-resolution (≥720p) slow-motion sports videos crawled from YouTube. We re-train several state-of-the-art methods on our benchmark, and the results show a decrease in their accuracy compared to other datasets.”

Find the paper and full list of authors at ArXiv.