XClipGS: Exact Half-Space Clipping for Medical Volume Gaussian Splatting
Not on the map. Why?
Abstract (arXiv)
Gaussian-splatting proxies enable interactive rendering of volumetric medical scans, but a clipping plane exposes anatomy not constrained by external-view training and intersects primitives that conventional splatting can only keep or drop whole. We present XClipGS (eXact Clipping), which treats these as two separate problems: the render-time clip operator and supervision of the hidden interior. Under the local affine model used by EWA splatting, the ray integral of a half-space-restricted Gaussian factorizes exactly into its ordinary 2D footprint and a conditional Gaussian CDF whose argument is affine in pixel coordinates. The resulting closed-form per-pixel operator introduces no learned clipping parameters or auxiliary network and remains differentiable with respect to the primitive and plane. We use multi-distance reference views with varied clipping-plane axes and offsets to supervise the interior through the same operator. We also introduce a paired clipped/unclipped cut-face protocol with difference-referenced cut error (CDE) and culled-side leakage (Leak), because global image metrics dilute errors near the plane. On eight CT and MRI volumes with plane offsets not used for training, XClipGS attains the highest PSNR on every volume (33.56 versus 32.34 dB for ClipGS) while rendering at over 650 FPS, far above real time, versus 278 FPS. On voxel-axis cut-face views, it raises average band SSIM from 0.809 to 0.860 and leaks roughly 40 times less. Without retraining, it also achieves the best average across all four metrics on arbitrary-normal planes; on a fixed interior, it matches RaRa's face fidelity with about 16 times less leakage. Project page: https://gaozhongpai.github.io/XClipGS/
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 19 of its 34 references that are in the map. First posted on arXiv 7 Aug 2026.
Builds on
19 of 34 references.
References · 19
- 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
- 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,141
- 2023Gaussian Grouping: Segment and Edit Anything in 3D Scenescited by 387
- 2023Feature 3DGS: Supercharging 3D Gaussian Splatting to Enable Distilled Feature Fieldscited by 361
- 2023GaussianEditor: Swift and Controllable 3D Editing with Gaussian Splattingcited by 331
- 2024Speedy-Splat: Fast 3D Gaussian Splatting with Sparse Pixels and Sparse Primitivescited by 90
- 2024Analytic-Splatting: Anti-Aliased 3D Gaussian Splatting via Analytic Integrationcited by 66
- 20243D-HGS: 3D Half-Gaussian Splattingcited by 43
- 2024Deform3DGS: Flexible Deformation for Fast Surgical Scene Reconstruction with Gaussian Splattingcited by 37
- 2024DDGS-CT: Direction-Disentangled Gaussian Splatting for Realistic Volume Renderingcited by 22
- 2024Application of 3D Gaussian Splatting for Cinematic Anatomy on Consumer Class Devicescited by 16
- 20257DGS: Unified Spatial-Temporal-Angular Gaussian Splattingcited by 16
7 more
- 20246DGS: Enhanced Direction-Aware Gaussian Splatting for Volumetric Renderingcited by 14
- 2025TC-GS: A Faster Gaussian Splatting Module Utilizing Tensor Corescited by 12
- 20253DGEER: 3D Gaussian Rendering Made Exact and Efficient for Generic Camerascited by 8
- 2024Multi-Layer Gaussian Splatting for Immersive Anatomy Visualizationcited by 7
- 2016Shaping the Future through Innovations: From Medical Imaging to Precision Medicinecited by 4
- 2025Render-FM: Feedforward Model for Real-time Photorealistic Volumetric Renderingcited by 3
- 2025RaRa Clipper: A Clipper for Gaussian Splatting Based on Ray Tracer and Rasterizercited by 1
Built on by
Not cited yet.