Learning a High Fidelity Pose Invariant Model for High-resolution Face Frontalization
This work addresses the problem of high-resolution face frontalization for applications like pose-invariant face recognition, though it appears incremental as it builds on existing methods with novel components.
The paper tackles the challenge of synthesizing high-resolution frontal face views from profile images, proposing a High Fidelity Pose Invariant Model (HF-PIM) that achieves photographic and identity-preserving results, improving both face recognition performance and frontalization appearances.
Face frontalization refers to the process of synthesizing the frontal view of a face from a given profile. Due to self-occlusion and appearance distortion in the wild, it is extremely challenging to recover faithful results and preserve texture details in a high-resolution. This paper proposes a High Fidelity Pose Invariant Model (HF-PIM) to produce photographic and identity-preserving results. HF-PIM frontalizes the profiles through a novel texture warping procedure and leverages a dense correspondence field to bind the 2D and 3D surface spaces. We decompose the prerequisite of warping into dense correspondence field estimation and facial texture map recovering, which are both well addressed by deep networks. Different from those reconstruction methods relying on 3D data, we also propose Adversarial Residual Dictionary Learning (ARDL) to supervise facial texture map recovering with only monocular images. Exhaustive experiments on both controlled and uncontrolled environments demonstrate that the proposed method not only boosts the performance of pose-invariant face recognition but also dramatically improves high-resolution frontalization appearances.