SportsSloMo: A New Benchmark and Baselines for Human-centric Video Frame Interpolation
This addresses a gap in sports analysis and entertainment by providing a challenging benchmark for slow-motion video synthesis, though it is incremental as it builds on existing methods with new data and loss terms.
The authors tackled the lack of a dedicated benchmark for human-centric video frame interpolation by introducing SportsSloMo, a dataset with over 130K clips and 1M frames from sports videos, and found that existing methods show decreased accuracy on it, but they improved performance by adding human-aware loss terms that boosted 5 models.
Human-centric video frame interpolation has great potential for improving people's entertainment experiences and finding commercial applications in the sports analysis industry, e.g., synthesizing slow-motion videos. 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 ($\geq$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. It highlights the difficulty of our benchmark and suggests that it poses significant challenges even for the best-performing methods, as human bodies are highly deformable and occlusions are frequent in sports videos. To improve the accuracy, we introduce two loss terms considering the human-aware priors, where we add auxiliary supervision to panoptic segmentation and human keypoints detection, respectively. The loss terms are model agnostic and can be easily plugged into any video frame interpolation approaches. Experimental results validate the effectiveness of our proposed loss terms, leading to consistent performance improvement over 5 existing models, which establish strong baseline models on our benchmark. The dataset and code can be found at: https://neu-vi.github.io/SportsSlomo/.