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
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.
By Zhongpai Gao, Benjamin Planche, Meng Zheng, Anwesa Choudhuri, Chaoyi Zhou, Terrence Chen, Ziyan Wu
arXiv:2610.10225v1 Announce Type: new
Abstract: Whole slide image (WSI) analysis in computational pathology follows a multiple instance learning (MIL) pipeline where patch embeddings are extracted in...
By Haoyu He, Basile Tessier-Cloutier, Yang Wang, Mahdi S. Hosseini
arXiv:2609.01516v1 Announce Type: new
Abstract: While 3D Gaussian Splatting (3DGS) has revolutionized 3D reconstruction and novel-view synthesis, scenarios with limited input views often lead to poor...
By Qian Wang, Yu Wang, Weiqi Li, Xinhua Cheng, Xiandong Meng, Ronggang Wang, Jian Zhang
DAGS introduces a lightweight, attention‑free conditioning scheme that disentangles appearance and geometry for a frozen image diffusion transformer (DiT), enabling high‑fidelity, temporally stable renders with independent control. Two small convolutional encoders generate per‑frame conditioning features, which are injected as learned residuals into the image tokens, avoiding the quadratic cost of attention. Coupled with a recurrent lighting stabilizer and a training‑free temporal guidance term, DAGS transforms a per‑frame image model into a streaming renderer that outperforms real‑time denoisers and diffusion renderers in PSNR and temporal stability while requiring far less compute than path tracing.
By Karthik Mohan Kumar, Damian Andrysiak, Pedro Antonio Pena, Kunal Tyagi, Rama Harihara
TileSkipper introduces a region‑adaptive tile pruning strategy for 3D Gaussian splatting rasterizers, assigning a static per‑Gaussian contribution cutoff policy that is calibrated on a frozen checkpoint. The method partitions Gaussians into 64 groups, uses a single‑byte policy per Gaussian, and requires no runtime updates or additional kernels. Across 13 benchmark scenes, TileSkipper achieves up to 1.238× speedups with negligible PSNR loss, and integrates with existing opacity‑aware bounds for further compiler‑only gains.
By Jingxing Li, Yongjae Lee, Deliang Fan, Abhay Kumar Yadav, Cheng Peng, Rama Chellappa