# FactorSplat: Appearance-Controllable Gaussian Proxies for Medical Volume Rendering

arXiv: https://arxiv.org/abs/2610.02382 · HTML: https://mlsanity.com/paper/2610.02382/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 24 references that are in the map.
- First posted on arXiv 1 Oct 2026.

## Builds on (most cited first, 20 of 20)

- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [DeepONet: Learning nonlinear operators for identifying differential equations based on the universal approximation theorem of operators](https://mlsanity.com/paper/1910.03193/) (2019)
- [Deep Sets](https://mlsanity.com/paper/1703.06114/) (2017)
- [HyperNetworks](https://mlsanity.com/paper/1609.09106/) (2016)
- [Mip-Splatting: Alias-free 3D Gaussian Splatting](https://mlsanity.com/paper/2311.16493/) (2023)
- [A Generative Model for Volume Rendering](https://mlsanity.com/paper/1710.09545/) (2017)
- [7DGS: Unified Spatial-Temporal-Angular Gaussian Splatting](https://mlsanity.com/paper/2503.07946/) (2025)
- [iVR-GS: Inverse Volume Rendering for Explorable Visualization via Editable 3D Gaussian Splatting](https://mlsanity.com/paper/2504.17954/) (2025)
- [Application of 3D Gaussian Splatting for Cinematic Anatomy on Consumer Class Devices](https://mlsanity.com/paper/2404.11285/) (2024)
- [Differentiable Direct Volume Rendering](https://mlsanity.com/paper/2107.12672/) (2021)
- [6DGS: Enhanced Direction-Aware Gaussian Splatting for Volumetric Rendering](https://mlsanity.com/paper/2410.04974/) (2024)
- [ViSNeRF: Efficient Multidimensional Neural Radiance Field Representation for Visualization Synthesis of Dynamic Volumetric Scenes](https://mlsanity.com/paper/2502.16731/) (2025)
- [Text-based Transfer Function Design for Semantic Volume Rendering](https://mlsanity.com/paper/2406.15634/) (2024)
- [Volume Encoding Gaussians: Transfer Function-Agnostic 3D Gaussians for Volume Rendering](https://mlsanity.com/paper/2504.13339/) (2025)
- [Render-FM: Feedforward Model for Real-time Photorealistic Volumetric Rendering](https://mlsanity.com/paper/2505.17338/) (2025)
- [Universal Beta Splatting](https://mlsanity.com/paper/2510.03312/) (2025)
- [ECoNGS: Efficient Compressive Neural Gaussian Splats for Volume Visualization](https://mlsanity.com/paper/2607.18466/) (2026)
- [Leveraging Self-Supervised Vision Transformers for Segmentation-based Transfer Function Design](https://mlsanity.com/paper/2309.01408/) (2023)
- [3D Gaussian Splatting for Scientific Particle Data Compression and Rendering](https://mlsanity.com/paper/2607.22956/) (2026)
- [GS-Surrogate: Deformable Gaussian Splatting for Parameter Space Exploration of Ensemble Simulations](https://mlsanity.com/paper/2604.06358/) (2026)

## Abstract (arXiv)

Transfer functions (TFs) control color and visibility in medical volume rendering, but image-trained Gaussian proxies typically bake one transfer function into their appearance. We present FactorSplat, a per-scene N-dimensional Gaussian splatting (N-DGS) proxy that accepts region-specific intensity-to-RGBA curves at inference. A local lookup applies the authored color and opacity change, while a shared functional encoder and low-rank per-Gaussian factors learn the residual appearance response. Geometry and directional appearance remain shared across presets, with visibility control and TF-aware pruning preserving the ability to hide and reveal structures. On seven CT and MR scans, FactorSplat improves mean PSNR and changed-region error over region-aware VEG across validation, interpolation, unseen composition, and out-of-distribution (OOD) edits. Across these four splits, seven-scan mean PSNR gains over VEG range from 1.10 to 1.52 dB. One checkpoint per scan supports unseen edits without retraining. At 16002, the cached fast renderer averages 524 FPS with 1.17 ms TF switches. Project page: https://gaozhongpai.github.io/FactorSplat/.