2021 International Conference on 3D Vision (3DV) · 2021 · 72 citations · 52 references
ComputingComputer Science3D ModelingComputational GeometryComputer Vision3D ReconstructionFace RecognitionGeometry ProcessingMulti-view GeometrySurface ReconstructionThree-dimensional Reconstruction3D Face Recognition3D Facial Reconstruction3D Shape ReconstructionFace AlignmentFace RepresentationFacial Landmark DetectionLandmark-based ReconstructionMorphable Shape Models
The study investigates a synergy between 3D Morphable Models and 3D facial landmarks to predict complete 3D facial geometry, including alignment, orientation, and modeling. The authors design a representation cycle that alternately refines 3DMM parameters and 3D landmarks, using each to predict the other, and employ simple network operations to achieve fast, accurate geometry prediction. Extensive validation on full facial geometry prediction tasks demonstrates superior and robust performance across various scenarios. Codes and data are available at https://choyingw.github.io/works/SynergyNet/.
This work studies learning from a synergy process of 3D Morphable Models (3DMM) and 3D facial landmarks to predict complete 3D facial geometry, including 3D alignment, face orientation, and 3D face modeling. Our synergy process leverages a representation cycle for 3DMM parameters and 3D landmarks. 3D landmarks can be extracted and refined from face meshes built by 3DMM parameters. We next reverse the representation direction and show that predicting 3DMM parameters from sparse 3D landmarks improves the information flow. Together we create a synergy process that utilizes the relation between 3D landmarks and 3DMM parameters, and they collaboratively contribute to better performance. We extensively validate our contribution on full tasks of facial geometry prediction and show our superior and robust performance on these tasks for various scenarios. Particularly, we adopt only simple and widely-used network operations to attain fast and accurate facial geometry prediction. Codes and data: https: //choyingw.github.io/works/SynergyNet/.
52
PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
Raffaelli Charles, Hao Su, Kaichun Mo et al. · 2017 · 9.8K citations
One millisecond face alignment with an ensemble of regression trees
Vahid Kazemi, Josephine Sullivan · 2014 · 2.8K citations · Full text
A 3D Face Model for Pose and Illumination Invariant Face Recognition
Pascal Paysan, Reinhard Knothe, Brian Amberg et al. · 2009 · 1.4K citations