mlsanityData to 7 Oct 2026

PillarGen: Enhancing Radar Point Cloud Density and Quality via Pillar-based Point Generation Network

arXiv 2403.01663 ↗First posted 4 Mar 2024cs.CVcited by 2

Not on the map. Why?

Abstract (arXiv)

In this paper, we present a novel point generation model, referred to as Pillar-based Point Generation Network (PillarGen), which facilitates the transformation of point clouds from one domain into another. PillarGen can produce synthetic point clouds with enhanced density and quality based on the provided input point clouds. The PillarGen model performs the following three steps: 1) pillar encoding, 2) Occupied Pillar Prediction (OPP), and 3) Pillar to Point Generation (PPG). The input point clouds are encoded using a pillar grid structure to generate pillar features. Then, OPP determines the active pillars used for point generation and predicts the center of points and the number of points to be generated for each active pillar. PPG generates the synthetic points for each active pillar based on the information provided by OPP. We evaluate the performance of PillarGen using our proprietary radar dataset, focusing on enhancing the density and quality of short-range radar data using the long-range radar data as supervision. Our experiments demonstrate that PillarGen outperforms traditional point upsampling methods in quantitative and qualitative measures. We also confirm that when PillarGen is incorporated into bird's eye view object detection, a significant improvement in detection accuracy is achieved.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 40 of its 52 references that are in the map. First posted on arXiv 4 Mar 2024.

Builds on

40 of 52 references.

References · 40

  1. 2017Attention Is All You Needcited by 59,932
  2. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  3. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,530
  4. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
  5. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,485
  6. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  7. 2014Sequence to Sequence Learning with Neural Networkscited by 2,974
  8. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  9. 2018PointPillars: Fast Encoders for Object Detection from Point Cloudscited by 1,707
  10. 2017StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translationcited by 1,036
  11. 2015Effective Approaches to Attention-based Neural Machine Translationcited by 1,024
  12. 2016A Point Set Generation Network for 3D Object Reconstruction from a Single Imagecited by 972
28 more
  1. 2018PointCNN: Convolution On X-Transformed Pointscited by 764
  2. 2021Diffusion Probabilistic Models for 3D Point Cloud Generationcited by 734
  3. 2019PointFlow: 3D Point Cloud Generation with Continuous Normalizing Flowscited by 487
  4. 2018PCN: Point Completion Networkcited by 382
  5. 2021PoinTr: Diverse Point Cloud Completion with Geometry-Aware Transformerscited by 284
  6. 2016Shape Completion using 3D-Encoder-Predictor CNNs and Shape Synthesiscited by 219
  7. 2018PU-Net: Point Cloud Upsampling Networkcited by 208
  8. 2020GRNet: Gridding Residual Network for Dense Point Cloud Completioncited by 174
  9. 2019PU-GAN: a Point Cloud Upsampling Adversarial Networkcited by 162
  10. 2020Point Cloud Completion by Skip-attention Network with Hierarchical Foldingcited by 106
  11. 2018PointGrow: Autoregressively Learned Point Cloud Generation with Self-Attentioncited by 105
  12. 2018Patch-based Progressive 3D Point Set Upsamplingcited by 101
  13. 2019PU-GCN: Point Cloud Upsampling using Graph Convolutional Networkscited by 100
  14. 2018Multiresolution Tree Networks for 3D Point Cloud Processingcited by 91
  15. 2022Learning to Generate Realistic LiDAR Point Cloudscited by 91
  16. 2017High-Resolution Shape Completion Using Deep Neural Networks for Global Structure and Local Geometry Inferencecited by 87
  17. 2022SeedFormer: Patch Seeds based Point Cloud Completion with Upsample Transformercited by 83
  18. 2023UltraLiDAR: Learning Compact Representations for LiDAR Completion and Generationcited by 76
  19. 2021Point Cloud Upsampling via Disentangled Refinementcited by 74
  20. 2020PUGeo-Net: A Geometry-centric Network for 3D Point Cloud Upsamplingcited by 69
  21. 2019Multi-Angle Point Cloud-VAE: Unsupervised Feature Learning for 3D Point Clouds from Multiple Angles by Joint Self-Reconstruction and Half-to-Half Predictioncited by 66
  22. 2021Cycle4Completion: Unpaired Point Cloud Completion using Cycle Transformation with Missing Region Codingcited by 50
  23. 2023NeRF-LiDAR: Generating Realistic LiDAR Point Clouds with Neural Radiance Fieldscited by 44
  24. 2021Voxel-based Network for Shape Completion by Leveraging Edge Generationcited by 32
  25. 2021PU-Transformer: Point Cloud Upsampling Transformercited by 32
  26. 2022LAKe-Net: Topology-Aware Point Cloud Completion by Localizing Aligned Keypointscited by 27
  27. 2020Skeleton-bridged Point Completion: From Global Inference to Local Adjustmentcited by 23
  28. 2021PC2-PU: Patch Correlation and Point Correlation for Effective Point Cloud Upsamplingcited by 11

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 1.

2 papers.

  1. 2025Unsupervised Radar Point Cloud Enhancement via Arbitrary LiDAR Guided Diffusion Priorcited by 2
  2. 2026SDCM: Simulated Densifying and Compensatory Modeling Fusion for Radar-Vision 3-D Object Detection in Internet of Vehiclescited by 0