Slow - Motion Video Synthesis for Basketball Using Frame Interpolation

TL;DR

This paper introduces a real-time, high-quality basketball slow-motion video synthesis system by fine-tuning the RIFE network on a sports-specific dataset, outperforming existing methods in accuracy and speed.

Contribution

The authors adapt the RIFE network for basketball slow-motion video synthesis through sports-specific fine-tuning, achieving superior quality and real-time performance.

Findings

Fine-tuned RIFE achieves 34.3 dB PSNR and 0.949 SSIM.

Outperforms Super SloMo and baseline RIFE in quality metrics.

Generates 4x slow-motion at 30 fps on consumer hardware.

Abstract

Basketball broadcast footage is traditionally captured at 30-60 fps, limiting viewers' ability to appreciate rapid plays such as dunks and crossovers. We present a real-time slow-motion synthesis system that produces high-quality basketball-specific interpolated frames by fine-tuning the recent Real-Time Intermediate Flow Estimation (RIFE) network on the SportsSloMo dataset. Our pipeline isolates the basketball subset of SportsSloMo, extracts training triplets, and fine-tunes RIFE with human-aware random cropping. We compare the resulting model against Super SloMo and the baseline RIFE model using Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity (SSIM) on held-out clips. The fine-tuned RIFE attains a mean PSNR of 34.3 dB and SSIM of 0.949, outperforming Super SloMo by 2.1 dB and the baseline RIFE by 1.3 dB. A lightweight Gradio interface demonstrates end-to-end 4x slow-motion generation on a single RTX 4070 Ti Super at approximately 30 fps. These results indicate that task-specific adaptation is crucial for sports slow-motion, and that RIFE provides an attractive accuracy-speed trade-off for consumer applications.