Single-View 3D Face Reconstruction via Cross-View Consistency Constraints
Deep neural network-based unsupervised single-view 3D face reconstruction has achieved re-markable success.Existing work relied on the photometric rendering constraint and the symmetric regulari-zation to learn from 2D single-view facial images.However,the single view facial images lack reliable face geometric and texture constraints due to self-occlusion and illumination variations.In this paper,we propose a two-stage single-view 3D face reconstruction framework by virtue of cross-view consistent constraints.First,the part network(PartNet)with parallel branches is used to estimate the view-dependent pixel-wise UV positional and albedo maps.The missing geometries and textures due to self-occlusion are filled by the low-dimensional statistical facial 3DMM model.Second,the complete network(CompNet)is used to refine the UV positional and albedo maps with geometry and texture details.We design a cross-view consistency constraint in terms of photometric rendering,facial texture,and UV positional maps.The proposed end-to-end model is optimized from the multi-view facial image datasets in an unsupervised manner.Ex-periments show that the proposed method is effective in accurately aligning faces and inferring reliable faci-al geometries and textures in self-occlusion regions from a single-view image.Our method is feasible to re-construct high-fidelity 3D faces with geometry and texture details.Specifically,the proposed method reduc-es the root mean square error by 6.36％compared with the state-of-the-art on MICC Florence dataset.
3D face reconstructionmulti-view consistency constraintUV position map
NETL
NSTL
万方数据
