Papers
Topics
Authors
Recent
Detailed Answer
Quick Answer
Concise responses based on abstracts only
Detailed Answer
Well-researched responses based on abstracts and relevant paper content.
Custom Instructions Pro
Preferences or requirements that you'd like Emergent Mind to consider when generating responses
Gemini 2.5 Flash
Gemini 2.5 Flash 45 tok/s
Gemini 2.5 Pro 54 tok/s Pro
GPT-5 Medium 22 tok/s Pro
GPT-5 High 20 tok/s Pro
GPT-4o 99 tok/s Pro
Kimi K2 183 tok/s Pro
GPT OSS 120B 467 tok/s Pro
Claude Sonnet 4 39 tok/s Pro
2000 character limit reached

PillarGen: Enhancing Radar Point Cloud Density and Quality via Pillar-based Point Generation Network (2403.01663v2)

Published 4 Mar 2024 in cs.CV

Abstract: 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.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (51)
  1. Learning representations and generative models for 3d point clouds. In International conference on machine learning, pages 40–49. PMLR, 2018.
  2. Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473, 2014.
  3. nuscenes: A multimodal dataset for autonomous driving. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 11621–11631, 2020.
  4. Anchorformer: Point cloud completion from discriminative nodes. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 13581–13590, 2023.
  5. Stargan: Unified generative adversarial networks for multi-domain image-to-image translation. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 8789–8797, 2018.
  6. Shape completion using 3d-encoder-predictor cnns and shape synthesis. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 5868–5877, 2017.
  7. A point set generation network for 3d object reconstruction from a single image. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 605–613, 2017.
  8. Multiresolution tree networks for 3d point cloud processing. In Proceedings of the European Conference on Computer Vision (ECCV), pages 103–118, 2018.
  9. High-resolution shape completion using deep neural networks for global structure and local geometry inference. In Proceedings of the IEEE international conference on computer vision, pages 85–93, 2017.
  10. Multi-angle point cloud-vae: Unsupervised feature learning for 3d point clouds from multiple angles by joint self-reconstruction and half-to-half prediction. In 2019 IEEE/CVF International Conference on Computer Vision (ICCV), pages 10441–10450. IEEE, 2019.
  11. Image-to-image translation with conditional adversarial networks. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 1125–1134, 2017.
  12. Grif net: Gated region of interest fusion network for robust 3d object detection from radar point cloud and monocular image. In 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pages 10857–10864. IEEE, 2020.
  13. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980, 2014.
  14. Pointpillars: Fast encoders for object detection from point clouds. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 12697–12705, 2019.
  15. Pu-gan: a point cloud upsampling adversarial network. In Proceedings of the IEEE/CVF international conference on computer vision, pages 7203–7212, 2019.
  16. Point cloud upsampling via disentangled refinement. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 344–353, 2021.
  17. Pointcnn: Convolution on x-transformed points. Advances in neural information processing systems, 31, 2018.
  18. Focal loss for dense object detection. In Proceedings of the IEEE international conference on computer vision, pages 2980–2988, 2017.
  19. Pc2-pu: Patch correlation and point correlation for effective point cloud upsampling. In Proceedings of the 30th ACM International Conference on Multimedia, pages 2191–2201, 2022.
  20. Diffusion probabilistic models for 3d point cloud generation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 2837–2845, 2021.
  21. Effective approaches to attention-based neural machine translation. arXiv preprint arXiv:1508.04025, 2015.
  22. A field model for repairing 3d shapes. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 5676–5684, 2016.
  23. Skeleton-bridged point completion: From global inference to local adjustment. Advances in Neural Information Processing Systems, 33:16119–16130, 2020.
  24. Pointnet: Deep learning on point sets for 3d classification and segmentation. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 652–660, 2017.
  25. Pointnet++: Deep hierarchical feature learning on point sets in a metric space. Advances in neural information processing systems, 30, 2017.
  26. Pu-gcn: Point cloud upsampling using graph convolutional networks. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 11683–11692, 2021.
  27. Pugeo-net: A geometry-centric network for 3d point cloud upsampling. In European conference on computer vision, pages 752–769. Springer, 2020.
  28. Pu-transformer: Point cloud upsampling transformer. In Proceedings of the Asian Conference on Computer Vision, pages 2475–2493, 2022.
  29. Diffusion-based signed distance fields for 3d shape generation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 20887–20897, 2023.
  30. 3d point cloud generative adversarial network based on tree structured graph convolutions. In Proceedings of the IEEE/CVF international conference on computer vision, pages 3859–3868, 2019.
  31. Pointgrow: Autoregressively learned point cloud generation with self-attention. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, pages 61–70, 2020.
  32. Sequence to sequence learning with neural networks. Advances in neural information processing systems, 27, 2014.
  33. Lake-net: Topology-aware point cloud completion by localizing aligned keypoints. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 1726–1735, 2022.
  34. Learning localized generative models for 3d point clouds via graph convolution. In International conference on learning representations, 2018.
  35. Attention is all you need. Advances in neural information processing systems, 30, 2017.
  36. Voxel-based network for shape completion by leveraging edge generation. In Proceedings of the IEEE/CVF international conference on computer vision, pages 13189–13198, 2021.
  37. Dynamic graph cnn for learning on point clouds. ACM Transactions on Graphics (tog), 38(5):1–12, 2019.
  38. Cycle4completion: Unpaired point cloud completion using cycle transformation with missing region coding. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 13080–13089, 2021.
  39. Point cloud completion by skip-attention network with hierarchical folding. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 1939–1948, 2020.
  40. Grnet: Gridding residual network for dense point cloud completion. In European Conference on Computer Vision, pages 365–381. Springer, 2020.
  41. Learning compact representations for lidar completion and generation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 1074–1083, 2023.
  42. Pointflow: 3d point cloud generation with continuous normalizing flows. In Proceedings of the IEEE/CVF international conference on computer vision, pages 4541–4550, 2019.
  43. Foldingnet: Point cloud auto-encoder via deep grid deformation. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 206–215, 2018.
  44. Patch-based progressive 3d point set upsampling. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 5958–5967, 2019.
  45. Pu-net: Point cloud upsampling network. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 2790–2799, 2018.
  46. Pointr: Diverse point cloud completion with geometry-aware transformers. In Proceedings of the IEEE/CVF international conference on computer vision, pages 12498–12507, 2021.
  47. Pcn: Point completion network. In 2018 international conference on 3D vision (3DV), pages 728–737. IEEE, 2018.
  48. Nerf-lidar: Generating realistic lidar point clouds with neural radiance fields. arXiv preprint arXiv:2304.14811, 2023.
  49. Seedformer: Patch seeds based point cloud completion with upsample transformer. In European conference on computer vision, pages 416–432. Springer, 2022.
  50. Unpaired image-to-image translation using cycle-consistent adversarial networks. In Proceedings of the IEEE international conference on computer vision, pages 2223–2232, 2017.
  51. Learning to generate realistic lidar point clouds. In European Conference on Computer Vision, pages 17–35. Springer, 2022.

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
List To Do Tasks Checklist Streamline Icon: https://streamlinehq.com

Collections

Sign up for free to add this paper to one or more collections.

User Circle Single Streamline Icon: https://streamlinehq.com Sign Up
Lightbulb On Streamline Icon: https://streamlinehq.com

Continue Learning

We haven't generated follow-up questions for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Generate Now