Skip to content
Preprint

ESVR: 3D Ellipsoid-based Sparse Volume Rendering via Structure-aware Primitive Learning and Per-primitive Ray Sampling

Aug 2026 · 0 citations · 61 references
Computer Science

TL;DR

ESVR is proposed, an ellipsoid-based sparse volume rendering framework that directly learns and renders volumetric data in 3D space and achieves up to four orders of magnitude compression and real-time rendering at 43-223 FPS while maintaining competitive reconstruction quality.

Abstract

Efficient representation and rendering of large-scale sparse volumetric data remain challenging in scientific visualization, as meaningful structures often occupy only a small fraction of the spatial domain. While direct volume rendering (DVR) provides high-quality visualization, its computational and memory costs scale poorly with data size. Recent advances in 3D Gaussian Splatting (3DGS) address this challenge by representing volumetric scenes with compact geometric primitives, enabling efficient, high-fidelity rendering. However, existing 3DGS-based methods learn from DVR rendered images rather than raw volumes, leading to information loss and limiting flexible transfer function control for interactive exploration. To address these limitations, we propose ESVR, an ellipsoid-based sparse volume rendering framework that directly learns and renders volumetric data in 3D space. Our method combines differentiable ellipsoidal primitives with bounded support, structure-aware primitive learning with complementary pruning, and a per-primitive ray sampling strategy for fast and accurate transfer function mapping. To support large-scale datasets, we further introduce a chunk-based optimization scheme with ghost ellipsoids, providing boundary context during training. Across large sparse datasets, ESVR achieves up to four orders of magnitude compression and real-time rendering at 43-223 FPS while maintaining competitive reconstruction quality.

View source

Similar papers

Book Open access Oct 2026

WebSVR: Joint Volume Measurement and Novel View Synthesis in Web-based 3D Environments

Traditional 3D representation models, such as 3D meshes and 3D point clouds, provide accurate geometric measurements but lack the visual fidelity of modern novel view synthesis approaches. In contrast, recent differentiable rendering methods, such as Plenoxels and Gaussian Splatting, enable photorealistic real-time vis...

Raphael Kunert, R. Richter, Jürgen Döllner · 0 citations
Preprint Oct 2026

CompactSplat: Spatially Adaptive Gaussian Distribution for Feedforward Scene Reconstruction

Reconstructing 3D scenes from sparse views without per-scene optimization remains highly challenging, especially for recovering accurate geometry and fine textures. While recent feedforward approaches leverage generalizable 3D Gaussian Splatting (3DGS) for scene generation, they typically assign one or multiple Gaussia...

Bing He, Jing-Nan Gao, Yu-Nuo Chen et al. · 0 citations
Aug 2026

InfoLoD: Training-Data-Free Hierarchical 3D Gaussian Splatting via Fisher-Guided View Synthesis.

InfoLoD introduces a Fisher-guided self-distillation scheme that uses the Fisher Information Matrix to select geometrically valid, information-rich pseudo viewpoints, enabling LoD training directly from a pre-trained 3DGS model without any original images.

Zhenyu Xia, Pengcheng Han, Lin Chen et al. · 0 citations
Preprint Sep 2026

AnyGS2Mesh: Feed-Forward Mesh Reconstruction from 3D Gaussian Splatting with Arbitrary-Resolution Views

AnyGS2Mesh is presented, the first feed-forward framework for directly reconstructing 3D meshes from 3D Gaussian Splatting representations with support for arbitrary input image resolutions, and demonstrates the potential of combining Gaussian representations and feed-forward Transformer architectures for scalable 3D g...

Yuxuan Song, Fan Gao, Yi-Bo Zhao et al. · 0 citations
Preprint Sep 2026

CVT-GS: Learning to Simplify 3D Gaussian Splatting with Centroidal Voronoi Tessellation

This paper proposes CVT-GS, a novel optimization-free post-hoc simplification framework that directly compresses trained 3DGS scenes without sacrificing visual fidelity and outputs a standard 3DGS scene that is seamlessly compatible with existing renderers.

Bing-Xian Li, Yi-Long Li, Jing-Liang Peng et al. · 0 citations
Sep 2026

Voxel Grid-Based Depth Recovery From Monocular Structured Light.

We introduce an approach for depth estimation from images captured by monocular structured light systems, building upon the matching-free differentiable rendering paradigm with a key architectural contribution: replacing the implicit signed distance function (SDF) geometry representation with an explicit density voxel...

Zhuo-Hang Yu, Kai Wang, Ju-Yong Zhang · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.