Efficient Branching Cascaded Regression for Face Alignment under Significant Head Rotation

TL;DR

This paper introduces an efficient branching cascaded regression method for face alignment that robustly handles 180-degree head rotations using 2D training data, improving accuracy and speed for profile faces.

Contribution

It proposes a novel branching cascaded regression framework that simplifies the regression tasks and models pose-related landmark visibility with SPDMs, enabling robust face alignment under large head rotations.

Findings

Handles 180-degree head rotations without view-based models

Achieves real-time performance on in-the-wild profile faces

Outperforms existing methods in accuracy on challenging datasets

Abstract

Despite much interest in face alignment in recent years, the large majority of work has focused on near-frontal faces. Algorithms typically break down on profile faces, or are too slow for real-time applications. In this work we propose an efficient approach to face alignment that can handle 180 degrees of head rotation in a unified way (e.g., without resorting to view-based models) using 2D training data. The foundation of our approach is cascaded shape regression (CSR), which has emerged recently as the leading strategy. We propose a generalization of conventional CSRs that we call branching cascaded regression (BCR). Conventional CSRs are single-track; that is, they progress from one cascade level to the next in a straight line, with each regressor attempting to fit the entire dataset. We instead split the regression problem into two or more simpler ones after each cascade level. Intuitively, each regressor can then operate on a simpler objective function (i.e., with fewer conflicting gradient directions). Within the BCR framework, we model and infer pose-related landmark visibility and face shape simultaneously using Structured Point Distribution Models (SPDMs). We propose to learn task-specific feature mapping functions that are adaptive to landmark visibility, and that use SPDM parameters as regression targets instead of 2D landmark coordinates. Additionally, we introduce a new in-the-wild dataset of profile faces to validate our approach.