2017/02/28 by Luo Jiang, Juyong Zhang, Bailin Deng +2
Computer Science · Engineering · #3D Shape Modeling and Analysis #Advanced Vision and Imaging #Algorithm #Animation #Artificial intelligence #Bilinear interpolation #Computer graphics (images) #Computer science #Computer vision #Consistency (knowledge bases) #Face (sociological concept) #Face recognition and analysis #Image (mathematics) #Photometric stereo #Projection (relational algebra) #RGB color model #cs.CV
paper · pdf · doi:10.1109/tip.2018.2845697
Accepted by IEEE Transactions on Image Processing, 2018
openalex publication_date 2018/06/08 · arxiv created 2018/06/11 · arxiv updated 2018/08/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05
3D face reconstruction from a single image is a classical and challenging problem, with wide applications in many areas. Inspired by recent works in face animation from RGBD or monocular video inputs, we develop a novel method for reconstructing 3D faces from unconstrained 2D images, using a coarse-to-fine optimization strategy. First, a smooth coarse 3D face is generated from an example-based bilinear face model, by aligning the projection of 3D face landmarks with 2D landmarks detected from the input image. Afterwards, using local corrective deformation fields, the coarse 3D face is refined using photometric consistency constraints, resulting in a medium face shape. Finally, a shape-from-shading method is applied on the medium face to recover fine geometric details. Our method outperforms stateof- the-art approaches in terms of accuracy and detail recovery, which is demonstrated in extensive experiments using real world models and publicly available datasets.