Interactive 3D caricature generation based on double sampling

摘要: Recently, 3D caricature generation and applications have attracted wide attention from both the research community entertainment industry. This paper proposes a novel interactive approach for various interesting based on double sampling. Firstly, according to user's operation, we obtain coarse with local features transformation by sampling in well-built principle component analysis (PCA) subspace. Secondly, utilize information of 2D dataset, sample linear embedding (LLE) manifold Finally, use learned further refine applying Kriging interpolation. The experiments show that generated our method can preserve highly artistic styles also reflect intention.