Analysis of Sampling Strategies for Implicit 3D Reconstruction

In the training process of the implicit 3D reconstruction network, the choice of spatial query points’ sampling strategy affects the final performance of the model. Different works have differences in the selection of sampling strategies, not only in the spatial distribution of query points but also in the order of magnitude difference in the density of query points. For how to select the sampling strategy of query points, current works are more akin to an enumerating operation to find the optimal solution, which seriously affects work efficiency. In this work, we explore the relationship between the sampling strategy and the final performance of the network through classification analysis and experimental comparison. We divide related works into three categories according to the similarities and differences of the network structure and the experimental results verify the rationality of our classification. Therefore, we carry out an in-depth discussion on the relationship between the network type and the sampling strategy. In addition, we also discuss the impact of sampling strategy on the model performance from the aspect of implicit function types. Finally, we discuss the important role of sampling density in balancing model performance and reducing experimental overhead.