mlsanityData to 14 Oct 2026

Arbitrary Point Cloud Upsampling with Spherical Mixture of Gaussians

arXiv 2208.05274 ↗First posted 10 Aug 2022cs.CVcited by 6

Not on the map. Why?

Abstract (arXiv)

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/

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 33 of its 41 references that are in the map. First posted on arXiv 10 Aug 2022.

Builds on

33 of 41 references.

References · 33

  1. 2017Attention Is All You Needcited by 60,361
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  3. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  4. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 5,045
  5. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  6. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,223
  7. 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,200
  8. 2020Point Transformercited by 1,470
  9. 2020PCT: Point cloud transformercited by 732
  10. 2018Open3D: A Modern Library for 3D Data Processingcited by 721
  11. 2018AtlasNet: A Papier-Mach'e Approach to Learning 3D Surface Generationcited by 539
  12. 2019Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Datacited by 532
21 more
  1. 2021An End-to-End Transformer Model for 3D Object Detectioncited by 329
  2. 2021PoinTr: Diverse Point Cloud Completion with Geometry-Aware Transformerscited by 286
  3. 2018PU-Net: Point Cloud Upsampling Networkcited by 209
  4. 2019PU-GAN: a Point Cloud Upsampling Adversarial Networkcited by 164
  5. 2019Modeling Point Clouds with Self-Attention and Gumbel Subset Samplingcited by 151
  6. 2018Patch-based Progressive 3D Point Set Upsamplingcited by 101
  7. 2019PU-GCN: Point Cloud Upsampling using Graph Convolutional Networkscited by 101
  8. 2018EC-Net: an Edge-aware Point set Consolidation Networkcited by 84
  9. 2021Point Cloud Upsampling via Disentangled Refinementcited by 74
  10. 2021LCDNet: Deep Loop Closure Detection and Point Cloud Registration for LiDAR SLAMcited by 67
  11. 2021Neural Points: Point Cloud Representation with Neural Fields for Arbitrary Upsamplingcited by 48
  12. 2021Self-Supervised Pillar Motion Learning for Autonomous Drivingcited by 44
  13. 2021Meta-PU: An Arbitrary-Scale Upsampling Network for Point Cloudcited by 35
  14. 2021PU-Transformer: Point Cloud Upsampling Transformercited by 32
  15. 2020Deep Magnification-Flexible Upsampling over 3D Point Cloudscited by 27
  16. 2020Cloud Transformers: A Universal Approach To Point Cloud Processing Taskscited by 24
  17. 2020TearingNet: Point Cloud Autoencoder to Learn Topology-Friendly Representationscited by 23
  18. 2021Learning 3D Dense Correspondence via Canonical Point Autoencodercited by 21
  19. 2021SP-GAN: Sphere-Guided 3D Shape Generation and Manipulationcited by 21
  20. 2020PointAR: Efficient Lighting Estimation for Mobile Augmented Realitycited by 19
  21. 2022PU-EVA: An Edge Vector based Approximation Solution for Flexible-scale Point Cloud Upsamplingcited by 16

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 2; 2024: 2; 2025: 1.

6 papers.

  1. 2022Low-Rank Tensor Function Representation for Multi-Dimensional Data Recoverycited by 46
  2. 2023Learning Continuous Implicit Field with Local Distance Indicator for Arbitrary-Scale Point Cloud Upsamplingcited by 19
  3. 2023iPUNet:Iterative Cross Field Guided Point Cloud Upsamplingcited by 4
  4. 2024Deep Learning for 3D Point Cloud Enhancement: A Surveycited by 4
  5. 2024ModelNet-O: A Large-Scale Synthetic Dataset for Occlusion-Aware Point Cloud Classificationcited by 3
  6. 2025PU-Gaussian: Point Cloud Upsampling using 3D Gaussian Representationcited by 1