This paper presents a new locally refined collision detection approach for large scale complex meshes in distributed virtual environments (DVEs) where exact and interactive interference detection is required. Transmitting models with millions of polygons is time consuming in comparison with transmitting simple models. Even if the models are transmitted in progressive manner, the earlier received models are in low level-of-detail (LOD) because the models are refined globally. Increasing the accuracy of collision detection (CD) at the client still takes time because increasing the LOD of the model is a slow process. The new approach is composed of an AB-tree collision query algorithm and a new mesh refinement algorithm on a space partitioned mesh (SPM) representation. It deals with this problem by selectively refining the models at certain areas that are predicted to collide with other objects and transmitting the refined parts instead of the entire model from server to client. The accuracy of CD is increased quickly at the predicted contact areas. An interactive rate is guaranteed by reducing network response time and dynamically adjusting the complexity and the space cost of the collision query algorithm.