In recent years, there has been a significant increase in focus on the interpolation task of
computer vision. Despite the tremendous advancement of video interpolation, point cloud
interpolation remains insufficiently explored. Meanwhile, the existence of numerous
nonlinear large motions in real-world scenarios makes the point cloud interpolation task
more challenging. In light of these issues, we present NeuralPCI: an end-to-end 4D spatio-
temporal Neural field for 3D Point Cloud Interpolation, which implicitly integrates multi-frame …

In this document, we present more details and several extra results as well as visualization.
In Appendix B, we introduce details of the datasets used in our work. Then we elaborate on
the implementation details of our NeuralPCI and other baselines in Appendix C. And in
Appendix D, we provide extra results in multiple aspects, such as the convergence, different
numbers of input frames, explicit versus implicit frame interpolation, varying point cloud
densities and ground point removal. Finally, we show more qualitative results in Appendix E.