The Mixture Graph-A Data Structure for Compressing, Rendering, and Querying Segmentation Histograms

TL;DR

The paper introduces the Mixture Graph, a new data structure that compresses, renders, and queries segmentation histograms efficiently, enabling fast visualization and analysis of volumetric segmentation data.

Contribution

It presents a novel DAG-based data structure that factorizes mixtures into linear interpolations, allowing efficient storage, rendering, and querying of segmentation histograms in volumetric data.

Findings

Achieves up to 178× speed-up in histogram queries.

Enables interactive volume lighting and segmentation exploration.

Provides efficient compression and rendering for large volumetric datasets.

Abstract

In this paper, we present a novel data structure, called the Mixture Graph. This data structure allows us to compress, render, and query segmentation histograms. Such histograms arise when building a mipmap of a volume containing segmentation IDs. Each voxel in the histogram mipmap contains a convex combination (mixture) of segmentation IDs. Each mixture represents the distribution of IDs in the respective voxel's children. Our method factorizes these mixtures into a series of linear interpolations between exactly two segmentation IDs. The result is represented as a directed acyclic graph (DAG) whose nodes are topologically ordered. Pruning replicate nodes in the tree followed by compression allows us to store the resulting data structure efficiently. During rendering, transfer functions are propagated from sources (leafs) through the DAG to allow for efficient, pre-filtered rendering at interactive frame rates. Assembly of histogram contributions across the footprint of a given volume allows us to efficiently query partial histograms, achieving up to 178$\times$ speed-up over na$\mathrm{\"{i}}$ve parallelized range queries. Additionally, we apply the Mixture Graph to compute correctly pre-filtered volume lighting and to interactively explore segments based on shape, geometry, and orientation using multi-dimensional transfer functions.