# Frequency-Selective Geometry Upsampling of Point Clouds

arXiv: https://arxiv.org/abs/2205.01458 · HTML: https://mlsanity.com/paper/2205.01458/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 23 references that are in the map.
- First posted on arXiv 3 May 2022.

## Builds on (most cited first, 9 of 9)

- [Multi-View 3D Object Detection Network for Autonomous Driving](https://mlsanity.com/paper/1611.07759/) (2016)
- [PU-Net: Point Cloud Upsampling Network](https://mlsanity.com/paper/1801.06761/) (2018)
- [PU-GAN: a Point Cloud Upsampling Adversarial Network](https://mlsanity.com/paper/1907.10844/) (2019)
- [Patch-based Progressive 3D Point Set Upsampling](https://mlsanity.com/paper/1811.11286/) (2018)
- [EC-Net: an Edge-aware Point set Consolidation Network](https://mlsanity.com/paper/1807.06010/) (2018)
- [Point Cloud Upsampling via Disentangled Refinement](https://mlsanity.com/paper/2106.04779/) (2021)
- [3D Point Cloud Super-Resolution via Graph Total Variation on Surface Normals](https://mlsanity.com/paper/1908.06261/) (2019)
- [Frequency-Selective Mesh-to-Mesh Resampling for Color Upsampling of Point Clouds](https://mlsanity.com/paper/2203.09224/) (2022)
- [Resampling Images to a Regular Grid from a Non-Regular Subset of Pixel Positions Using Frequency Selective Reconstruction](https://mlsanity.com/paper/2204.12873/) (2022)

## Built on by (most cited first, 2 of 2)

- [Joint Geometry and Attribute Upsampling of Point Clouds Using Frequency-Selective Models with Overlapped Support](https://mlsanity.com/paper/2301.11630/) (2023)
- [Point Cloud Upsampling through Patch-based Frequency Superposition](https://mlsanity.com/paper/2606.14355/) (2026)

## Abstract (arXiv)

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.