F-Hash: Feature-Based Hash Design for Time-Varying Volume Visualization via Multi-Resolution Tesseract Encoding

2025-07-04

AI Summary

Training implicit neural representations (INRs) for time-varying volumetric data suffers from slow convergence and insufficient efficiency for interactive visualization. Method: We propose F-Hash encoding—a novel architecture that introduces the 4D hypercube (tesseract) structure into dynamic hash encoding, enabling conflict-free, multi-level feature-aware hashing to achieve high encoding capacity with compact parameters. Integrated with a 4D embedded grid and an adaptive ray-marching algorithm, F-Hash unifies INR training and rendering optimization. Contribution/Results: The method natively supports diverse time-varying feature detection and spatiotemporal super-resolution reconstruction. Evaluated on multiple large-scale time-varying volume datasets, it achieves state-of-the-art training convergence speed and significantly improves rendering frame rates—enabling real-time interactive visualization.

Technology Category

• Computer Vision: 3D Computer Vision
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Machine Learning: Representation Learning

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs

Abstract

Interactive time-varying volume visualization is challenging due to its complex spatiotemporal features and sheer size of the dataset. Recent works transform the original discrete time-varying volumetric data into continuous Implicit Neural Representations (INR) to address the issues of compression, rendering, and super-resolution in both spatial and temporal domains. However, training the INR takes a long time to converge, especially when handling large-scale time-varying volumetric datasets. In this work, we proposed F-Hash, a novel feature-based multi-resolution Tesseract encoding architecture to greatly enhance the convergence speed compared with existing input encoding methods for modeling time-varying volumetric data. The proposed design incorporates multi-level collision-free hash functions that map dynamic 4D multi-resolution embedding grids without bucket waste, achieving high encoding capacity with compact encoding parameters. Our encoding method is agnostic to time-varying feature detection methods, making it a unified encoding solution for feature tracking and evolution visualization. Experiments show the F-Hash achieves state-of-the-art convergence speed in training various time-varying volumetric datasets for diverse features. We also proposed an adaptive ray marching algorithm to optimize the sample streaming for faster rendering of the time-varying neural representation.

Problem

• Enhance convergence speed for time-varying volume visualization
• Optimize encoding for dynamic 4D multi-resolution feature grids
• Improve rendering efficiency via adaptive ray marching

Innovation

• Feature-based multi-resolution Tesseract encoding architecture
• Multi-level collision-free hash functions for dynamic 4D grids
• Adaptive ray marching algorithm for faster rendering