← Back to all news
arXiv Computer Vision By Zhongpai Gao, Benjamin Planche, Meng Zheng, Anwesa Choudhuri, Chaoyi Zhou, Terrence Chen, Ziyan Wu

XClipGS: Exact Half-Space Clipping for Medical Volume Gaussian Splatting

Read the original on arXiv Computer Vision →

XClipGS introduces an exact half‑space clipping method for Gaussian‑splatting of medical volumes, enabling precise rendering of clipped anatomy without learned clipping parameters. The technique factorizes the ray integral into a 2D footprint and a conditional Gaussian CDF, remaining differentiable and efficient. Evaluated on eight CT and MRI datasets, XClipGS outperforms prior methods in PSNR, SSIM, and leakage while achieving over 650 FPS.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

Related stories

arXiv AI
Jun 24

Render-FM: Feedforward Model for Real-time Photorealistic Volumetric Rendering

arXiv:2505. 17338v3 Announce Type: replace-cross Abstract: Photorealistic volumetric rendering of CT scans greatly benefits clinical workflows, yet neural approaches such as Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS) require prohibitive per-scan optimization (hours for NeRF, about 30 minutes for 3DGS), making them impractical in clinical settings.

By Zhongpai Gao, Benjamin Planche, Meng Zheng, Anwesa Choudhuri, Van Nguyen Nguyen, Terrence Chen, Ziyan Wu
computer-visionfine-tuning
More like this →
arXiv Computer Vision
Oct 5

FactorSplat: Appearance-Controllable Gaussian Proxies for Medical Volume Rendering

FactorSplat introduces a per-scene N‑dimensional Gaussian splatting proxy that allows region‑specific intensity‑to‑RGBA curves to be applied at inference, enabling appearance control in medical volume rendering. The method uses a shared functional encoder and low‑rank per‑Gaussian factors to learn residual appearance while keeping geometry and directional appearance shared across presets. Experiments on seven CT and MR scans show that FactorSplat outperforms region‑aware VEG in mean PSNR and changed‑region error across validation, interpolation, unseen composition, and out‑of‑distribution edits, achieving 1.10 to 1.52 dB PSNR gains and supporting fast TF switches at 524 FPS.

By Zhongpai Gao, Benjamin Planche, Meng Zheng, Anwesa Choudhuri, Terrence Chen, Ziyan Wu
efficiency
More like this →
arXiv AI
Aug 19

Learning Where and What to Lift for Bi-planar X-ray-to-CT Reconstruction

The paper introduces LiftXR, a geometry‑guided framework that first reconstructs a 3D anatomical layout from bi‑planar X‑ray images and then uses this layout to guide CT volume reconstruction. An anatomical parser refines the layout by analyzing the reconstructed CT, enabling region‑specific intensity calibration. Experiments on two public datasets show LiftXR surpasses recent X‑ray‑to‑CT methods and improves downstream segmentation performance.

By Yifei Wu, Yicheng Wu, Qiang Ma, Qi Chen, Renyang Gu, Xinyu Liu, Yongsheng Pan, Yong Xia
computer-vision
More like this →
arXiv Computer Vision
Aug 28

DALE-CT: Depth-Aware 2D Slice Encoders Learn an Anatomical World Model of Chest CT

DALE-CT introduces depth‑aware 2D slice encoders that learn an anatomical world model of chest CT scans without 3D or positional supervision. By sampling self‑supervised views across a physical $z$‑axis slab, the encoder captures how anatomy changes between neighboring slices, enabling it to recover slice ordering and distinguish slices by anatomy alone. The model, trained on a large 287k‑scan corpus, achieves state‑of‑the‑art performance on CT‑RATE and is released with full code and evaluation tools.

By Evan W. Damron, Mahmut S. Gokmen, Mitchell A. Klusty, Caroline N. Leach, Emily B. Collier, V. K. Cody Bumgardner
llms
More like this →