Kalman-Inspired Feature Propagation for Video Face Super-Resolution

TL;DR

This paper introduces Kalman-inspired Feature Propagation (KEEP), a novel framework for video face super-resolution that leverages Kalman filtering principles to maintain facial detail consistency across frames.

Contribution

We propose a new recurrent framework based on Kalman filtering principles to improve temporal consistency and facial detail preservation in video face super-resolution.

Findings

Effective in capturing facial details consistently across frames

Outperforms existing methods in maintaining temporal stability

Demonstrates significant improvements in visual quality

Abstract

Despite the promising progress of face image super-resolution, video face super-resolution remains relatively under-explored. Existing approaches either adapt general video super-resolution networks to face datasets or apply established face image super-resolution models independently on individual video frames. These paradigms encounter challenges either in reconstructing facial details or maintaining temporal consistency. To address these issues, we introduce a novel framework called Kalman-inspired Feature Propagation (KEEP), designed to maintain a stable face prior over time. The Kalman filtering principles offer our method a recurrent ability to use the information from previously restored frames to guide and regulate the restoration process of the current frame. Extensive experiments demonstrate the effectiveness of our method in capturing facial details consistently across video frames. Code and video demo are available at https://jnjaby.github.io/projects/KEEP.