mlsanityData to 14 Oct 2026

4DSR-GCN: 4D Video Point Cloud Upsampling using Graph Convolutional Networks

arXiv 2306.01081 ↗First posted 1 Jun 2023cs.CV cs.AI cs.MMcited by 1

Not on the map. Why?

Abstract (arXiv)

Time varying sequences of 3D point clouds, or 4D point clouds, are now being acquired at an increasing pace in several applications (e.g., LiDAR in autonomous or assisted driving). In many cases, such volume of data is transmitted, thus requiring that proper compression tools are applied to either reduce the resolution or the bandwidth. In this paper, we propose a new solution for upscaling and restoration of time-varying 3D video point clouds after they have been heavily compressed. In consideration of recent growing relevance of 3D applications, %We focused on a model allowing user-side upscaling and artifact removal for 3D video point clouds, a real-time stream of which would require . Our model consists of a specifically designed Graph Convolutional Network (GCN) that combines Dynamic Edge Convolution and Graph Attention Networks for feature aggregation in a Generative Adversarial setting. By taking inspiration PointNet++, We present a different way to sample dense point clouds with the intent to make these modules work in synergy to provide each node enough features about its neighbourhood in order to later on generate new vertices. Compared to other solutions in the literature that address the same task, our proposed model is capable of obtaining comparable results in terms of quality of the reconstruction, while using a substantially lower number of parameters (about 300KB), making our solution deployable in edge computing devices such as LiDAR.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 32 of its 48 references that are in the map. First posted on arXiv 1 Jun 2023.

Builds on

32 of 48 references.

References · 32

  1. 2017Graph Attention Networkscited by 8,923
  2. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  3. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  4. 2019Fast Graph Representation Learning with PyTorch Geometriccited by 2,434
  5. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,223
  6. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,041
  7. 2013Spectral Networks and Locally Connected Networks on Graphscited by 1,102
  8. 2016Least Squares Generative Adversarial Networkscited by 1,001
  9. 2016A Point Set Generation Network for 3D Object Reconstruction from a Single Imagecited by 979
  10. 2018PointCNN: Convolution On X-Transformed Pointscited by 764
  11. 2018Pixel2Mesh: Generating 3D Mesh Models from Single RGB Imagescited by 651
  12. 2017Frustum PointNets for 3D Object Detection from RGB-D Datacited by 640
20 more
  1. 2018AtlasNet: A Papier-Mach'e Approach to Learning 3D Surface Generationcited by 539
  2. 2016OctNet: Learning Deep 3D Representations at High Resolutionscited by 342
  3. 2016Shape Completion using 3D-Encoder-Predictor CNNs and Shape Synthesiscited by 219
  4. 2018PU-Net: Point Cloud Upsampling Networkcited by 209
  5. 2016Learning a Predictable and Generative Vector Representation for Objectscited by 173
  6. 2017SGPN: Similarity Group Proposal Network for 3D Point Cloud Instance Segmentationcited by 169
  7. 2019PU-GAN: a Point Cloud Upsampling Adversarial Networkcited by 164
  8. 2017Escape from Cells: Deep Kd-Networks for the Recognition of 3D Point Cloud Modelscited by 142
  9. 2017Learning Efficient Point Cloud Generation for Dense 3D Object Reconstructioncited by 133
  10. 2017Pointwise Convolutional Neural Networkscited by 127
  11. 2021Density-aware Chamfer Distance as a Comprehensive Metric for Point Cloud Completioncited by 112
  12. 2018Patch-based Progressive 3D Point Set Upsamplingcited by 101
  13. 2019PU-GCN: Point Cloud Upsampling using Graph Convolutional Networkscited by 101
  14. 2017PCPNET: Learning Local Shape Properties from Raw Point Cloudscited by 98
  15. 2018EC-Net: an Edge-aware Point set Consolidation Networkcited by 84
  16. 2020PUGeo-Net: A Geometry-centric Network for 3D Point Cloud Upsamplingcited by 69
  17. 2021Learning Parallel Dense Correspondence from Spatio-Temporal Descriptors for Efficient and Robust 4D Reconstructioncited by 31
  18. 2021Learning Compositional Representation for 4D Captures with Neural ODEcited by 22
  19. 2016Temporally coherent 4D reconstruction of complex dynamic scenescited by 21
  20. 2022RFNet-4D++: Joint Object Reconstruction and Flow Estimation from 4D Point Clouds with Cross-Attention Spatio-Temporal Featurescited by 5

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025Advances in 4D Representation: Geometry, Motion, and Interactioncited by 4