Robust 3D Face Shape Reconstruction from Single Images via Two-Fold Coupled Structure Learning and Off-the-Shelf Landmark Detectors
In Proceedings British Machine Vision Conference 2014
AbstractIn this paper, we propose a robust method for monocular face shape reconstruction (MFSR) using a sparse set of facial landmarks that are detected by most of the off-the-shelf landmark detectors. We formulate the MFSR problem as a two-Fold Coupled Structure Learning (2FCSL) process, which learns a two-fold coupled structure consisting of the regression between two subspaces spanned by 3D sparse landmarks and 2D sparse landmarks, respectively, and a coupled dictionary learned on 3D sparse and dense shape using K-SVD. To handle variations in face pose, we explicitly incorporate pose estimation in our method. Extensive experiments on both synthetic data and real data from two challenging datasets using manual and automatic landmarks show that our method is robust to pose variations and landmark localization noise and achieves state-of-the-art performance.
FilesExtended Abstract (PDF, 1 page, 618K)
Paper (PDF, 13 pages, 1.9M)