Face alignment by coarse-to-fine shape searching
We present a novel face alignment framework based on coarse-to-fine shape searching. Unlike the conventional cascaded regression approaches that start with an initial shape and refine 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 finer search of shapes. The unique stage-by-stage progressive and adaptive search i) prevents the final 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-the-art results on various benchmarks including the challenging 300-W dataset.
PDF Abstract 2015 IEEE 2015 PDF 2015 IEEE 2015 AbstractCode
Tasks
300W
Helen
LFPW
WFLW
AFLW-19
| Task | Dataset | Model | Metric Name | Metric Value | Global Rank | Benchmark |
|---|---|---|---|---|---|---|
| Face Alignment | AFLW-19 | CFSS | NME_diag (%, Full) | 3.92 | # 20 | |
| NME_diag (%, Frontal) | 2.68 | # 14 | ||||
| Face Alignment | WFLW | CFSS | NME (inter-ocular) | 9.07 | # 31 | |
| AUC@10 (inter-ocular) | 36.6 | # 25 | ||||
| FR@10 (inter-ocular) | 20.56 | # 26 |
