mlsanityData to 7 Oct 2026

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

arXiv 2504.17954 ↗First posted 24 Apr 2025cs.GR cs.CV cs.LGcited by 17

Not on the map. Why?

Abstract (arXiv)

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 paper 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.

Key facts. Cited by 17 papers in the map (data through 7 Oct 2026). Builds on 34 of its 60 references that are in the map. First posted on arXiv 24 Apr 2025.

Builds on

34 of 60 references.

References · 34

  1. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  2. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,141
  3. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,698
  4. 2021Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fieldscited by 2,013
  5. 2021Plenoxels: Radiance Fields without Neural Networkscited by 1,607
  6. 2020Neural Sparse Voxel Fieldscited by 959
  7. 2023Zip-NeRF: Anti-Aliased Grid-Based Neural Radiance Fieldscited by 667
  8. 2023LightGaussian: Unbounded 3D Gaussian Compression with 15x Reduction and 200+ FPScited by 420
  9. 2023Compressed 3D Gaussian Splatting for Accelerated Novel View Synthesiscited by 232
  10. 2023GS-IR: 3D Gaussian Splatting for Inverse Renderingcited by 220
  11. 2023TensoIR: Tensorial Inverse Renderingcited by 166
  12. 2023Tri-MipRF: Tri-Mip Representation for Efficient Anti-Aliasing Neural Radiance Fieldscited by 142
22 more
  1. 2024Reducing the Memory Footprint of 3D Gaussian Splattingcited by 129
  2. 2022ActiveNeRF: Learning where to See with Uncertainty Estimationcited by 124
  3. 2022NeILF: Neural Incident Light Field for Physically-based Material Estimationcited by 105
  4. 2022Compressible-composable NeRF via Rank-residual Decompositioncited by 92
  5. 2023NeILF++: Inter-Reflectable Light Fields for Geometry and Material Estimationcited by 73
  6. 2022Compressing Volumetric Radiance Fields to 1 MBcited by 66
  7. 2021Compressive Neural Representations of Volumetric Scalar Fieldscited by 64
  8. 2022Control-NeRF: Editable Feature Volumes for Scene Rendering and Manipulationcited by 57
  9. 2019InSituNet: Deep Image Synthesis for Parameter Space Exploration of Ensemble Simulationscited by 37
  10. 2021Fast Neural Representations for Direct Volume Renderingcited by 32
  11. 2022DL4SciVis: A State-of-the-Art Survey on Deep Learning for Scientific Visualizationcited by 32
  12. 2017A Generative Model for Volume Renderingcited by 30
  13. 2024Rip-NeRF: Anti-aliasing Radiance Fields with Ripmap-Encoded Platonic Solidscited by 23
  14. 2022VDL-Surrogate: A View-Dependent Latent-based Model for Parameter Space Exploration of Ensemble Simulationscited by 20
  15. 2022Interactive Volume Visualization via Multi-Resolution Hash Encoding based Neural Representationcited by 19
  16. 2023Adaptively Placed Multi-Grid Scene Representation Networks for Large-Scale Data Visualizationcited by 16
  17. 2023ECNR: Efficient Compressive Neural Representation of Time-Varying Volumetric Datasetscited by 16
  18. 2024Application of 3D Gaussian Splatting for Cinematic Anatomy on Consumer Class Devicescited by 16
  19. 2023SlimmeRF: Slimmable Radiance Fieldscited by 15
  20. 2024StyleRF-VolVis: Style Transfer of Neural Radiance Fields for Expressive Volume Visualizationcited by 9
  21. 2024SCARF: Scalable Continual Learning Framework for Memory-efficient Multiple Neural Radiance Fieldscited by 8
  22. 2024ParamsDrag: Interactive Parameter Space Exploration via Image-Space Draggingcited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 6; 2026: 11.

17 papers.

Sort:

By area:

  1. 2025NLI4VolVis: Natural Language Interaction for Volume Visualization via LLM Multi-Agents and Editable 3D Gaussian Splattingcited by 19
  2. 2025TexGS-VolVis: Expressive Scene Editing for Volume Visualization via Textured Gaussian Splattingcited by 9
  3. 2026SciVisAgentBench: A Benchmark for Evaluating Scientific Data Analysis and Visualization Agentscited by 9
  4. 2025IntuiTF: MLLM-Guided Transfer Function Optimization for Direct Volume Renderingcited by 4
  5. 2026SGI: Structured 2D Gaussians for Efficient and Compact Large Image Representationcited by 3
  6. 2025Scale-GS: Efficient Scalable Gaussian Splatting via Redundancy-filtering Training on Streaming Contentcited by 2
  7. 2025CloseUpShot: Close-up Novel View Synthesis from Sparse-views via Point-conditioned Diffusion Modelcited by 2
  8. 2026Efficient Compression of Structured and Unstructured Volumes via Learned 3D Gaussian Representationcited by 2
  9. 2026ECoNGS: Efficient Compressive Neural Gaussian Splats for Volume Visualizationcited by 2
  10. 2026HiLSVA: Design and Evaluation of a Human-in-the-Loop Agentic System for Scientific Visualizationcited by 1
  11. 2026Fixed-Budget Gaussian Volume Encoding with Structure-Aware Allocationcited by 1
  12. 2025Accurate and Complete Surface Reconstruction from 3D Gaussians via Direct SDF Learningcited by 0
5 more
  1. 2026Topo-GS: Continuous Volumetric Embedding of High-Dimensional Data via Topological Gaussian Splattingcited by 0
  2. 2026Lossless-INR: Lossless Volumetric Implicit Neural Representationscited by 0
  3. 2026EVOLVE: Efficient Learned Volume Compression with Variable-Rate Encoding on a Cross-Domain Databasecited by 0
  4. 2026Gaussian Volumetric Representation for Efficient Shear-Warp Visualizationcited by 0
  5. 20263D Field Data Reduction with Adaptive Sample-Based Gaussian-Encoded Reconstructioncited by 0