Perception-Oriented Video Frame Interpolation via Asymmetric Blending

CVPR 2024

This repository represents the official implementation of the paper titled "Perception-Oriented Video Frame Interpolation via Asymmetric Blending", also denoted as "PerVFI".

Guangyang Wu, Xin Tao, Changlin Li, Wenyi Wang, Xiaohong Liu, Qingqing Zheng

We present PerVFI, a novel paradigm for perception-oriented video frame interpolation.

Asymmetric synergistic blending scheme: reduce blurry and ghosting effects derived from unavoidable motion error.
Generative model as decoder: reconstruct results sampled from a distribution to resolve temporal supervision misalignment during training.
Future: network structure can be meticulously optimized to improve efficiency and performance in the future.

Detailed usage of this model can be found in GitHub Repo