Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
97 tokens/sec
GPT-4o
53 tokens/sec
Gemini 2.5 Pro Pro
44 tokens/sec
o3 Pro
5 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

ECLAIR: A High-Fidelity Aerial LiDAR Dataset for Semantic Segmentation (2404.10699v1)

Published 16 Apr 2024 in cs.CV

Abstract: We introduce ECLAIR (Extended Classification of Lidar for AI Recognition), a new outdoor large-scale aerial LiDAR dataset designed specifically for advancing research in point cloud semantic segmentation. As the most extensive and diverse collection of its kind to date, the dataset covers a total area of 10$km2$ with close to 600 million points and features eleven distinct object categories. To guarantee the dataset's quality and utility, we have thoroughly curated the point labels through an internal team of experts, ensuring accuracy and consistency in semantic labeling. The dataset is engineered to move forward the fields of 3D urban modeling, scene understanding, and utility infrastructure management by presenting new challenges and potential applications. As a benchmark, we report qualitative and quantitative analysis of a voxel-based point cloud segmentation approach based on the Minkowski Engine.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (47)
  1. 3d semantic parsing of large-scale indoor spaces. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 1534–1543, 2016.
  2. ARKitscenes - a diverse real-world dataset for 3d indoor scene understanding using mobile RGB-d data. In Advances in Neural Information Processing Systems (NeurIPS), Datasets and Benchmarks Track, 2021.
  3. SemanticKITTI: A Dataset for Semantic Scene Understanding of LiDAR Sequences. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), pages 9297–9307, 2019.
  4. The lovász-softmax loss: A tractable surrogate for the optimization of the intersection-over-union measure in neural networks. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 4413–4421, 2018.
  5. nuscenes: A multimodal dataset for autonomous driving. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 11621–11631, 2020.
  6. Semantic segmentation on swiss3dcities: A benchmark study on aerial photogrammetric 3d pointcloud dataset. Pattern Recognition Letters, 150:108–114, 2021.
  7. Matterport3d: Learning from rgb-d data in indoor environments. In International Conference on 3D Vision (3DV), pages 667–676, 2017.
  8. Argoverse: 3d tracking and forecasting with rich maps. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 8748–8757, 2019.
  9. Cenet: Toward concise and efficient lidar semantic segmentation for autonomous driving, 2022.
  10. 4d spatio-temporal convnets: Minkowski convolutional neural networks. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 3075–3084, 2019.
  11. Scannet: Richly-annotated 3d reconstructions of indoor scenes. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 5828–5839, 2017.
  12. Resunet-a: A deep learning framework for semantic segmentation of remotely sensed data. ISPRS Journal of Photogrammetry and Remote Sensing, 162:94–114, 2020.
  13. Vision meets robotics: The kitti dataset. International Journal of Robotics Research (IJRR), 2013.
  14. Semantic3d.net: A new large-scale point cloud classification benchmark, 2017.
  15. One thousand and one hours: Self-driving motion prediction dataset, 2020.
  16. Towards semantic segmentation of urban-scale 3d point clouds: A dataset, benchmarks and challenges. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 4977–4987, 2021.
  17. Adam: A method for stochastic optimization. In Proceedings of the International Conference on Learning Representations (ICLR), 2015.
  18. Segment anything, 2023.
  19. Pointpillars: Fast encoders for object detection from point clouds. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 12697–12705, 2019.
  20. Campus3d: A photogrammetry point cloud benchmark for hierarchical understanding of outdoor scene. In Proceedings of the 28th ACM International Conference on Multimedia, pages 238–246. Association for Computing Machinery, 2020.
  21. Pointcnn: Convolution on x-transformed points. In Advances in Neural Information Processing Systems (NeurIPS), pages 820–830. Curran Associates, Inc., 2018.
  22. Focal loss for dense object detection. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), pages 2999–3007, 2017.
  23. Voxnet: A 3d convolutional neural network for real-time object recognition. In Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pages 922–928, 2015.
  24. Semanticposs: A point cloud dataset with large quantity of dynamic instances. In 2020 IEEE Intelligent Vehicles Symposium (IV), pages 687–693, 2020.
  25. A*3d dataset: Towards autonomous driving in challenging environments. In Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), 2020.
  26. Learning transferable visual models from natural language supervision, 2021.
  27. Efficient 3d semantic segmentation with superpoint transformer. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), pages 17195–17204, 2023.
  28. The isprs benchmark on urban object classification and 3d building reconstruction. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, I-3:293–298, 2012.
  29. Paris-lille-3d: A large and high-quality ground-truth urban point cloud dataset for automatic segmentation and classification. The International Journal of Robotics Research, 37(6):545–557, 2018.
  30. Language-grounded indoor 3d semantic segmentation in the wild. In Proceedings of the European Conference on Computer Vision (ECCV), pages 125–141. Springer-Verlag, 2022.
  31. Lamar: Benchmarking localization and mapping for augmented reality, 2022.
  32. Indoor scene segmentation using a structured light sensor. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops, pages 601–608, 2011.
  33. Sun rgb-d: A rgb-d scene understanding benchmark suite. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 567–576, 2015.
  34. Scalability in perception for autonomous driving: Waymo open dataset. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 2446–2454, 2020.
  35. Toronto-3D: A large-scale mobile lidar dataset for semantic segmentation of urban roadways. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, pages 202–203, 2020.
  36. Llama: Open and efficient foundation language models, 2023.
  37. Dales: A large-scale aerial lidar data set for semantic segmentation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, pages 186–187, 2020.
  38. Seesaw loss for long-tailed instance segmentation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 9690–9699, 2021.
  39. O-cnn: octree-based convolutional neural networks for 3d shape analysis. ACM Trans. Graph., 36(4), 2017.
  40. Point transformer v2: Grouped vector attention and partition-based pooling. In Advances in Neural Information Processing Systems (NeurIPS), pages 33330–33342. Curran Associates, Inc., 2022.
  41. Towards large-scale 3d representation learning with multi-dataset point prompt training, 2023.
  42. Point transformer v3: Simpler, faster, stronger. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024.
  43. Lasdu: A large-scale aerial lidar dataset for semantic labeling in dense urban areas. ISPRS International Journal of Geo-Information, 9(7), 2020.
  44. Scannet++: A high-fidelity dataset of 3d indoor scenes. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), pages 12–22, 2023.
  45. Point transformer. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), pages 16259–16268, 2021.
  46. Gimo: Gaze-informed human motion prediction in context, 2022.
  47. Dublincity: Annotated lidar point cloud and its applications. In Proceedings of the British Machine Vision Conference (BMVC), 2019.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (5)
  1. Iaroslav Melekhov (23 papers)
  2. Anand Umashankar (1 paper)
  3. Hyeong-Jin Kim (7 papers)
  4. Vladislav Serkov (1 paper)
  5. Dusty Argyle (1 paper)

Summary

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

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