Landmark Detection and 3D Face Reconstruction for Caricature using a Nonlinear Parametric Model
This addresses the problem of 3D modeling for caricatures, which has rarely been studied, for applications in computer graphics and animation, though it is incremental as it builds on existing parametric models.
The paper tackles automatic landmark detection and 3D face reconstruction for caricatures, a challenging problem due to geometric and texture variations, by proposing a novel 3D approach that regresses 3D shape and orientation from 2D images, with experimental results showing effectiveness for various caricatures.
Caricature is an artistic abstraction of the human face by distorting or exaggerating certain facial features, while still retains a likeness with the given face. Due to the large diversity of geometric and texture variations, automatic landmark detection and 3D face reconstruction for caricature is a challenging problem and has rarely been studied before. In this paper, we propose the first automatic method for this task by a novel 3D approach. To this end, we first build a dataset with various styles of 2D caricatures and their corresponding 3D shapes, and then build a parametric model on vertex based deformation space for 3D caricature face. Based on the constructed dataset and the nonlinear parametric model, we propose a neural network based method to regress the 3D face shape and orientation from the input 2D caricature image. Ablation studies and comparison with state-of-the-art methods demonstrate the effectiveness of our algorithm design. Extensive experimental results demonstrate that our method works well for various caricatures. Our constructed dataset, source code and trained model are available at https://github.com/Juyong/CaricatureFace.