Skip to content
arXiv Game AI· Kenneth Alonso·· 2026-10-12AI score28

Low-cost deep learning for automated keyframe interpolation in sprite animation

Low-Cost Deep Learning for Automated Keyframe Interpolation in Sprite Animation

AI summary

This study proposes a U-Net-based method for generating in-between frames in sprite animation. On 42 test triplets, it achieves a mean FLIP error of 0.258, outperforming RIFE (0.313), Lucas-Kanade (0.449), and CyclicGen (0.603).

Source: arXiv Game AI · arxiv.org