LDDMM-Face: Large Deformation Diffeomorphic Metric Learning for Flexible and Consistent Face Alignment
This addresses the problem of flexible and consistent face alignment for computer vision applications, offering a novel method that improves handling of occlusions and annotation mismatches, though it is incremental in combining existing techniques.
The paper tackles face alignment by proposing LDDMM-Face, a framework that uses a deformation layer for diffeomorphic registration to predict facial landmarks, achieving comparable or superior performance to state-of-the-art methods on benchmark datasets like 300W and WFLW, with outstanding results in weakly-supervised learning and cross-dataset scenarios.
We innovatively propose a flexible and consistent face alignment framework, LDDMM-Face, the key contribution of which is a deformation layer that naturally embeds facial geometry in a diffeomorphic way. Instead of predicting facial landmarks via heatmap or coordinate regression, we formulate this task in a diffeomorphic registration manner and predict momenta that uniquely parameterize the deformation between initial boundary and true boundary, and then perform large deformation diffeomorphic metric mapping (LDDMM) simultaneously for curve and landmark to localize the facial landmarks. Due to the embedding of LDDMM into a deep network, LDDMM-Face can consistently annotate facial landmarks without ambiguity and flexibly handle various annotation schemes, and can even predict dense annotations from sparse ones. Our method can be easily integrated into various face alignment networks. We extensively evaluate LDDMM-Face on four benchmark datasets: 300W, WFLW, HELEN and COFW-68. LDDMM-Face is comparable or superior to state-of-the-art methods for traditional within-dataset and same-annotation settings, but truly distinguishes itself with outstanding performance when dealing with weakly-supervised learning (partial-to-full), challenging cases (e.g., occluded faces), and different training and prediction datasets. In addition, LDDMM-Face shows promising results on the most challenging task of predicting across datasets with different annotation schemes.