LassoNet: Deep Lasso-Selection of 3D Point Clouds

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

10 pages

References in corpus (5)

• Geometric deep learning: going beyond Euclidean data
• O-CNN: Octree-based Convolutional Neural Networks for 3D Shape Analysis
• Monte Carlo Convolution for Learning on Non-Uniformly Sampled Point Clouds
• Bayesian multi-domain learning for cancer subtype discovery from next-generation sequencing count data
• Interactive Visual Exploration of Halos in Large Scale Cosmology Simulation

Cited by in corpus (15)

• A Survey on ML4VIS: Applying Machine Learning Advances to Data Visualization
• PointDifformer: Robust Point Cloud Registration With Neural Diffusion and Transformer
• PointAugment: an Auto-Augmentation Framework for Point Cloud Classification
• MeTACAST: Target- and Context-aware Spatial Selection in VR
• SpatialTouch: Exploring Spatial Data Visualizations in Cross-reality
• ReViVD: Exploration and Filtering of Trajectories in an Immersive Environment using 3D Shapes
• Meta-PU: An Arbitrary-Scale Upsampling Network for Point Cloud
• MultiVision: Designing Analytical Dashboards with Deep Learning Based Recommendation
• Point Cloud Upsampling via Disentangled Refinement
• Deep Colormap Extraction from Visualizations
• Investigate Indistinguishable Points in Semantic Segmentation of 3D Point Cloud
• Local Latent Representation based on Geometric Convolution for Particle Data Feature Exploration
• UrbanVR: An immersive analytics system for context-aware urban design
• Viewpoint Recommendation for Point Cloud Labeling through Interaction Cost Modeling
• AI4VIS: Survey on Artificial Intelligence Approaches for Data Visualization