Frequency-Selective Geometry Upsampling of Point Clouds
This addresses the need for cost-effective high-resolution point clouds in applications like 3D scanning and computer vision, representing an incremental improvement over existing upsampling techniques.
The paper tackles the problem of upsampling low-resolution point clouds to high-resolution by proposing a frequency-selective geometry method that estimates local frequency models to approximate surfaces and insert points, achieving a 4.4 times smaller point-to-point error than the second best method for a scale factor of 4.
The demand for high-resolution point clouds has increased throughout the last years. However, capturing high-resolution point clouds is expensive and thus, frequently replaced by upsampling of low-resolution data. Most state-of-the-art methods are either restricted to a rastered grid, incorporate normal vectors, or are trained for a single use case. We propose to use the frequency selectivity principle, where a frequency model is estimated locally that approximates the surface of the point cloud. Then, additional points are inserted into the approximated surface. Our novel frequency-selective geometry upsampling shows superior results in terms of subjective as well as objective quality compared to state-of-the-art methods for scaling factors of 2 and 4. On average, our proposed method shows a 4.4 times smaller point-to-point error than the second best state-of-the-art PU-Net for a scale factor of 4.