ScaleFree: Dynamic KDE for Multiscale Point Cloud Exploration in VR

2026-01-28

AI Summary

This work addresses the challenge of interactively exploring large-scale, multi-scale point clouds in virtual reality, where preserving both global context and local detail is difficult, and dynamically generating continuous density fields for seamless scale transitions incurs prohibitive computational costs. To this end, the authors propose a GPU-accelerated adaptive kernel density estimation (KDE) method that, for the first time, enables real-time reconstruction of dynamic density fields supporting seamless multi-scale navigation in VR. By integrating GPU-based k-d tree spatial queries, intra-warp parallel reduction, and adaptive kernel selection, the approach achieves substantial computational efficiency. Experiments demonstrate speedups of several orders of magnitude over serial and multi-core CPU baselines, while user studies confirm significant improvements in both accuracy and interaction efficiency for multi-scale selection tasks.

Technology Category

• Computer Vision: 3D Computer Vision
• Machine Learning: Kernel Methods
• Data Mining & Knowledge Management: Scalability, Parallel & Distributed Systems

Application Category

• Security and Privacy: Large-scale security measurements
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• User Modeling, Personalization and Recommendation: Practical large-scale studies of user experience

Abstract

We present ScaleFree, a GPU-accelerated adaptive Kernel Density Estimation (KDE) algorithm for scalable, interactive multiscale point cloud exploration. With this technique, we cater to the massive datasets and complex multiscale structures in advanced scientific computing, such as cosmological simulations with billions of particles. Effective exploration of such data requires a full 3D understanding of spatial structures, a capability for which immersive environments such as VR are particularly well suited. However, simultaneously supporting global multiscale context and fine-grained local detail remains a significant challenge. A key difficulty lies in dynamically generating continuous density fields from point clouds to facilitate the seamless scale transitions: while KDE is widely used, precomputed fields restrict the accuracy of interaction and omit fine-scale structures, while dynamic computation is often too costly for real-time VR interaction. We address this challenge by leveraging GPU acceleration with k-d-tree-based spatial queries and parallel reduction within a thread group for on-the-fly density estimation. With this approach, we can recalculate scalar fields dynamically as users shift their focus across scales. We demonstrate the benefits of adaptive density estimation through two data exploration tasks: adaptive selection and progressive navigation. Through performance experiments, we demonstrate that ScaleFree with GPU-parallel implementation achieves orders-of-magnitude speedups over sequential and multi-core CPU baselines. In a controlled experiment, we further confirm that our adaptive selection technique improves accuracy and efficiency in multiscale selection tasks.

Problem

• multiscale point cloud
• interactive exploration
• density estimation
• virtual reality
• scale transition

Innovation

• adaptive KDE
• GPU acceleration
• multiscale point cloud
• virtual reality
• dynamic density estimation