Analysis of Sampling Strategies for Implicit 3D Reconstruction
This work addresses an incremental efficiency issue for researchers and practitioners in 3D reconstruction by optimizing sampling strategies to reduce computational overhead.
The paper tackled the problem of inefficient sampling strategies for query points in implicit 3D reconstruction networks, which currently rely on enumeration to find optimal solutions; it analyzed relationships between sampling strategies and network performance and proposed linear sampling and distance mask methods to improve generality and robustness.
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 explored the relationship between sampling strategy and network final performance through classification analysis and experimental comparison from three aspects: the relationship between network type and sampling strategy, the relationship between implicit function and sampling strategy, and the impact of sampling density on model performance. In addition, we also proposed two methods, linear sampling and distance mask, to improve the sampling strategy of query points, making it more general and robust.