Multi-Attribute Robust Component Analysis for Facial UV Maps

The collection of large-scale three-dimensional (3-D) face models has led to significant progress in the field of 3-D face alignment “in-the-wild,” with several methods being proposed toward establishing sparse or dense 3-D correspondences between a given 2-D facial image and a 3-D face model. Utilizing 3-D face alignment improves 2-D face alignment in many ways, such as alleviating issues with artifacts and warping effects in texture images. However, the utilization of 3-D face models introduces a new set of challenges for researchers. Since facial images are commonly captured in arbitrary recording conditions, a considerable amount of missing information and gross outliers is observed (e.g., due to self-occlusion, subjects wearing eye-glasses, and so on). To this end, in this paper we propose the Multi-Attribute Robust Component Analysis (MA-RCA), a novel technique that is suitable for facial UV maps containing a considerable amount of missing information and outliers, while additionally, elegantly incorporates knowledge from various available attributes, such as age and identity. We evaluate the proposed method on problems such as UV denoising, UV completion, facial expression synthesis, and age progression, where MA-RCA outperforms compared techniques.