TY - JOUR AB - Robust principal component analysis (RPCA) is a powerful method for learning low-rank feature representation of variousvisual data. However, for certain types as well as significant amount of error corruption, it fails to yield satisfactory results; a drawbackthat can be alleviated by exploiting domain-dependent prior knowledge or information. In this paper, we propose two models for theRPCA that take into account such side information, even in the presence of missing values. We apply this framework to the task of UVcompletion which is widely used in pose-invariant face recognition. Moreover, we construct a generative adversarial network (GAN) toextract side information as well as subspaces. These subspaces not only assist in the recovery but also speed up the process in caseof large-scale data. We quantitatively and qualitatively evaluate the proposed approaches through both synthetic data and fivereal-world datasets to verify their effectiveness. AU - Deng,J AU - Xue,N AU - Cheng,S AU - Panagakis,I AU - Zafeiriou,S DO - 10.1109/TPAMI.2019.2902556 EP - 2364 PY - 2019/// SN - 0162-8828 SP - 2349 TI - Side information for face completion: a robust PCA approach T2 - IEEE Transactions on Pattern Analysis and Machine Intelligence UR - http://dx.doi.org/10.1109/TPAMI.2019.2902556 UR - http://hdl.handle.net/10044/1/68700 VL - 41 ER -