Abstract

We present a novel face alignment framework based on coarse-to-fifine shape searching. Unlike the conventional cascaded regression approaches that start with an initial shape and refifine the shape in a cascaded manner, our approach begins with a coarse search over a shape space that contains diverse shapes, and employs the coarse solution to constrain subsequent fifiner search of shapes. The unique stage-by-stage progressive and adaptive search i) prevents the fifinal solution from being trapped in local optima due to poor initialisation, a common problem encountered by cascaded regression approaches; and ii) improves the robustness in coping with large pose variations. The framework demonstrates real-time performance and state-of-theart results on various benchmarks including the challenging 300-W dataset