Arbitrary Point Cloud Upsampling with Spherical Mixture of Gaussians

1VisLab Srl (an Ambarella Inc company), 2University of Bologna, 3University of Parma
*Equal Contribution
3DV 2022 (Oral)

APU-SMOG upsamples a sparse input point cloud with any desired scaling factor.

Abstract

Generating dense point clouds from sparse raw data benefits downstream 3D understanding tasks, but existing models are limited to a fixed upsampling ratio or to a short range of integer values. In this paper, we present APU-SMOG, a Transformer-based model for Arbitrary Point cloud Upsampling (APU). The sparse input is firstly mapped to a Spherical Mixture of Gaussians (SMOG) distribution, from which an arbitrary number of points can be sampled. Then, these samples are fed as queries to the Transformer decoder, which maps them back to the target surface. Extensive qualitative and quantitative evaluations show that APU-SMOG outperforms state-of-the-art fixed-ratio methods, while effectively enabling upsampling with any scaling factor, including non-integer values, with a single trained model.

Video

BibTeX

@article{delleva2022arbitrary,
  author    = {Dell'Eva, Anthony and Orsingher, Marco and Bertozzi, Massimo},
  title     = {Arbitrary Point Cloud Upsampling with Spherical Mixture of Gaussians},
  journal   = {3DV},
  year      = {2022},
}