Work

iVR-GS: Inverse Volume Rendering for Explorable Visualization via Editable 3D Gaussian Splatting

Year: 2025

Type: article

Abstract: In volume visualization, users can interactively explore the three-dimensional data by specifying color and opacity mappings in the transfer function (TF) or adjusting lighting parameters, facilitating meaningful interpretation of the underlying structure. However, rendering large-scale volumes demands powerful GPUs and high-speed memory access for real-time performance. While existing novel view synthesis (NVS) methods offer faster rendering speeds with lower hardware requirements, the visible parts of a reconstructed scene are fixed and constrained by preset TF settings, significantly limiting user exploration. This article introduces inverse volume rendering via Gaussian splatting (iVR-GS), an innovative NVS method that reduces the rendering cost while enabling scene editing for interactive volume exploration. Specifically, we compose multiple iVR-GS models associated with basic TFs covering disjoint visible parts to make the entire volumetric scene visible. Each basic model contains a collection of 3D editable Gaussians, where each Gaussian is a 3D spatial point that supports real-time scene rendering and editing. We demonstrate the superior reconstruction quality and composability of iVR-GS against other NVS solutions (Plenoxels, CCNeRF, and base 3DGS) on various volume datasets. The code is available at https://github.com/TouKaienn/iVR-GS.

Source: IEEE Transactions on Visualization and Computer Graphics

DOI: 10.1109/tvcg.2025.3567121

Authors: Kaiyuan Tang, Siyuan Yao, Chaoli Wang

Institution: University of Notre Dame

Language: English

Topic: Computer Graphics and Visualization Techniques

Subfield: Computer Graphics and Computer-Aided Design

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funders: National Science Foundation, U.S. Department of Energy

Awards: III: Small: Neural Field Representations for Scientific Visualization, III: Small: DeepRep: Unsupervised Deep Representation Learning for Scientific Data Analysis and Visualization, IMPLICIT CONTINUOUS REPRESENTATIONS FOR VISUALIZATION OF COMPLEX DATA, III: Medium: Collaborative Research: Deep Learning for In Situ Analysis and Visualization, OAC Core: A Machine Learning Assisted Visual Analytics Approach for Understanding Flow Surfaces