Arbitrary Point Cloud Upsampling with Spherical Mixture of Gaussians
This addresses a bottleneck in 3D understanding tasks by allowing flexible point cloud upsampling, though it is incremental as it builds on existing Transformer and distribution-based methods.
The paper tackles the problem of generating dense point clouds from sparse data, which is limited by existing models to fixed or integer upsampling ratios, and presents APU-SMOG, a Transformer-based model that enables arbitrary upsampling ratios including non-integer values, outperforming state-of-the-art fixed-ratio methods in evaluations.
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. The code is available at https://github.com/apusmog/apusmog/