BlazeBVD addresses the critical need for compact representations in blind video deflickering. It utilizes scale-time equalization (STE) filtering in illumination space to correct global flicker and local exposed texture. The method consists of three stages: preparing deflickering priors, global and local flicker removal, and adaptive temporal consistency. BlazeBVD outperforms previous methods in terms of speed, fidelity maintenance, and temporal consistency.
In eine andere Sprache
aus dem Quellinhalt
arxiv.org
Wichtige Erkenntnisse aus
by Xinmin Qiu,C... um arxiv.org 03-12-2024
https://arxiv.org/pdf/2403.06243.pdfTiefere Fragen