Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
162 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

LassoNet: Deep Lasso-Selection of 3D Point Clouds (1907.13538v4)

Published 31 Jul 2019 in cs.HC and cs.GR

Abstract: Selection is a fundamental task in exploratory analysis and visualization of 3D point clouds. Prior researches on selection methods were developed mainly based on heuristics such as local point density, thus limiting their applicability in general data. Specific challenges root in the great variabilities implied by point clouds (e.g., dense vs. sparse), viewpoint (e.g., occluded vs. non-occluded), and lasso (e.g., small vs. large). In this work, we introduce LassoNet, a new deep neural network for lasso selection of 3D point clouds, attempting to learn a latent mapping from viewpoint and lasso to point cloud regions. To achieve this, we couple user-target points with viewpoint and lasso information through 3D coordinate transform and naive selection, and improve the method scalability via an intention filtering and farthest point sampling. A hierarchical network is trained using a dataset with over 30K lasso-selection records on two different point cloud data. We conduct a formal user study to compare LassoNet with two state-of-the-art lasso-selection methods. The evaluations confirm that our approach improves the selection effectiveness and efficiency across different combinations of 3D point clouds, viewpoints, and lasso selections. Project Website: https://lassonet.github.io

Definition Search Book Streamline Icon: https://streamlinehq.com
References (43)
  1. F. Argelaguet and C. Andujar. A survey of 3d object selection techniques for virtual environments. Computers & Graphics, 37(3):121–136, 2013.
  2. A theory of learning from different domains. Machine learning, 79(1-2):151–175, 2010.
  3. Geometric deep learning: Going beyond Euclidean data. IEEE Signal Processing Magazine, 34(4):18–42, 2017.
  4. M. M. Bronstein and I. Kokkinos. Scale-invariant heat kernel signatures for non-rigid shape recognition. In Proc. CVPR, pages 1704–1711, 2010.
  5. The farthest point strategy for progressive image sampling. IEEE TIP, 6(9):1305–1315, 1997.
  6. C. Fan and H. Hauser. Fast and accurate cnn-based brushing in scatterplots. Comput. Graph. Forum, 37(3):111–120, 2018.
  7. 3D Deep Shape Descriptor. In Proc. CVPR, pages 2319–2328, 2015.
  8. Aperture based selection for immersive virtual environments. In Proc. UIST, pages 95–96, 1996.
  9. Deep Learning. MIT Press, 2016. http://www.deeplearningbook.org.
  10. 3D mesh labeling via deep convolutional neural networks. ACM TOG, 35(1):3:1–3:12, 2015.
  11. Evaluating ‘graphical perception’ with CNNs. IEEE TVCG, 25(1):641–650, 2019.
  12. Bayesian multi-domain learning for cancer subtype discovery from next-generation sequencing count data. In Proc. NIPS, pages 9115–9124. Curran Associates, Inc., 2018.
  13. FlowNet: A Deep Learning Framework for Clustering and Selection of Streamlines and Stream Surfaces. IEEE TVCG, pages 1–1, 2018.
  14. Monte carlo convolution for learning on non-uniformly sampled point clouds. ACM TOG, 37(6), 2018.
  15. Visual Analytics in Deep Learning: An Interrogative Survey for the Next Frontiers. IEEE TVCG, pages 1–1, 2018.
  16. Recurrent slice networks for 3D segmentation of point clouds. In Proc. CVPR, pages 2626–2635, 2018.
  17. FiberClay: Sculpting Three Dimensional Trajectories to Reveal Structural Insights. IEEE TVCG, 25(1):704–714, 2019.
  18. ChartSense: Interactive data extraction from chart images. In Proc. ACM CHI, pages 6706–6717, 2017.
  19. D. F. Keefe and T. Isenberg. Reimagining the scientific visualization interaction paradigm. Computer, 46(5):51–57, 2013.
  20. 3D User Interfaces: Theory and Practice. Addison Wesley Longman Publishing Co., Inc., Redwood City, CA, USA, 2004.
  21. Pointcnn: Convolution on x-transformed points. In Proc. NIPS, pages 828–838, 2018.
  22. Towards Better Analysis of Machine Learning Models: A Visual Analytics Perspective. Visual Informatics, 1(1):48–56, 2017.
  23. ScatterNet: A deep subjective similarity model for visual analysis of scatterplots. IEEE TVCG, pages 1–1, 2018.
  24. Geodesic Convolutional Neural Networks on Riemannian Manifolds. IEEE ICCVW, pages 832–840, 2015.
  25. D. Maturana and S. Scherer. VoxNet: A 3D Convolutional Neural Network for Real-Time Object Recognition. In IEEE/RSJ Intel. Conf. Intelligent Robots and Systems, page 922 – 928, 2015.
  26. Volume catcher. In Proc. Symp. Interactive 3D Graphics and Games, pages 111–116, 2005.
  27. PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation. In Proc. CVPR, pages 652–660, 2017.
  28. PointNet++ : Deep Hierarchical Feature Learning on Point Sets in a Metric Space. Proc. NIPS, pages 5099–5108, 2017.
  29. Volumetric and Multi-View CNNs for Object Classification on 3D Data. In Proc. CVPR, pages 5648–5656, 2016.
  30. Interactive visual exploration of halos in large-scale cosmology simulation. Journal of Visualization, 17(3):145–156, 2014.
  31. A. Steed. Towards a general model for selection in virtual environments. In Proc. 3DUI, pages 103–110, Los Alamitos, 2006.
  32. A. Steed and C. Parker. 3D Selection Strategies for Head Tracked and Non-Head Tracked Operation of Spatially Immersive Displays. Proc. IIPT, pages 1–8, 2004.
  33. Multi-view convolutional neural networks for 3D shape recognition. In Proc. ICCV, pages 945–953, 2015.
  34. A concise and provably informative multi-scale signature based on heat diffusion. In Proc. Symp. Geometry Processing, pages 1383–1392, 1735621, 2009.
  35. Glyphlens: View-dependent occlusion management in the interactive glyph visualization. IEEE TVCG, 23(1):891–900, 2017.
  36. O-CNN: octree-based convolutional neural networks for 3D shape analysis. ACM TOG, 36(4):1–11, 2017.
  37. WYSIWYP: What You See Is What You Pick. IEEE TVCG, 18(12):2236–2244, 2012.
  38. G. J. Wills. Selection: 524,288 ways to say “this is interesting”. In Proc. IEEE InfoVis, pages 54–60, 1996.
  39. 3D ShapeNets: A Deep Representation for Volumetric Shapes. In Proc. CVPR, pages 1912–1920, 2015.
  40. 3D Recurrent Neural Networks with Context Fusion for Point Cloud Semantic Segmentation. In Proc. ECCV, pages 403–417, 2018.
  41. A scalable active framework for region annotation in 3D shape collections. ACM TOG, 35(6):210, 2016.
  42. Efficient Structure-Aware Selection Techniques for 3D Point Cloud Visualizations with 2DOF Input. IEEE TVCG, 18(12):2245–2254, 2012.
  43. CAST: Effective and Efficient User Interaction for Context-Aware Selection in 3D Particle Clouds. IEEE TVCG, 22(1):886–895, 2016.
Citations (42)
View on Semantic Scholar

Summary

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

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

Tweets