Correspondence attention for facial appearance simulation

Xi Fang, Daeseung Kim, Xuanang Xu, Tianshu Kuang, Nathan Lampen, Jungwook Lee, Hannah H. Deng, Michael A. K. Liebschner, James J. Xia, Jaime Gateno, Pingkun Yan

Abstract: Highlights•Attentive correspondence to facilitate movement transformation between point sets.•A novel contrastive loss to incorporate spatial proximity into feature correlation.•Visualization of the impact of attentive correspondence on facial simulation.•Same level of accuracy as FEM but considerably reduced computational time.