FactorSplat: Appearance-Controllable Gaussian Proxies for Medical Volume Rendering

arXiv:2610.02382v1 Announce Type: new Abstract: 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 1600^2, the cached fast renderer averages 524 FPS with 1.17 ms TF switches. Project page: https://gaozhongpai.github.io/FactorSplat/.

Related

• XClipGS: Exact Half-Space Clipping for Medical Volume Gaussian Splatting
• NVGS: Neural Visibility for Occlusion Culling in 3D Gaussian Splatting
• WilLaGS: Latent-Conditional 3D Appearance Fields for Robust Gaussian Splatting In-the-Wild
• MedGSSR: Generalizable Medical Image Super-Resolution 3D Reconstruction via Hierarchical Feed-forward Gaussian Splatting

Source: arXiv cs.CV | 2026-10-05