Abstract: Surface reconstruction (Bloomenthal and Wyvill, Introduction to Implicit Surfaces, 1997) is a fundamental work in Computer Aided Design (CAD) and Computer Graphics (CG). In this paper, motivated by the physical polar field model (Yuxu Lin Chun Chen in Proceedings of the 3rd Pacific-Rim Symposium on Image and Video Technology, 1997), we propose a novel implicit surface reconstruction approach, named Dual-RBF. Through simulating the physical polar field model, Dual-RBF provides a nice initial reconstruction state firstly. Then, two simple nonlinear methods are introduced to adjust the configurations of Dual-RBF model, so that a more accurate reconstruction is reached. Thirdly, the Dual-RBF becomes even more robust to fill the holes on some flawed input point-clouds by adopting a multi-level strategy. Finally, the visualization of the surface reconstruction is speed up with GPU. Experimental results show that the proposed approach is faster and more robust than previous implicit surface reconstruction techniques.