H-2DGS introduces a height-field 2D Gaussian Splatting pipeline that produces a sharp, deformable cortical surface reconstruction for neurosurgical navigation. The method concentrates a robust 3D Gaussian Splatting reconstruction, fuses its depth into a shared truncated signed distance field, and represents the surface with curved, surface-oriented Gaussian primitives. Across five real neurosurgical cases, H-2DGS achieves low multi-view depth inconsistency, a compact 7.97 MB representation, and interactive rendering at 29–42 ms per frame, integrating clearly with tractography and MRI anatomy.
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.
arXiv:2606. 07658v1 Announce Type: cross Abstract: Maximal safe resection is the primary objective in glioma surgery.
arXiv:2610.24858v2 Announce Type: replace Abstract: Reducing MRI acquisition time improves patient comfort, reduces motion artefacts, and increases scanner throughput. Clinical protocols often shorte...
arXiv:2609.22941v1 Announce Type: new Abstract: Novel view synthesis from sparse inputs remains challenging for 3D Gaussian Splatting (3DGS) due to ambiguous geometry, cross-view inconsistency, and m...
arXiv:2605.10360v3 Announce Type: replace Abstract: While novel view synthesis (NVS) for dynamic scenes has seen significant progress, reconstructing temporally consistent geometric surfaces remains...
arXiv:2605.26616v2 Announce Type: replace Abstract: While 3D Gaussian Splatting has achieved remarkable success in photorealistic novel view synthesis, its pursuit of fast and high-fidelity 3D recons...
The paper proposes using 3D Gaussian Splatting to reconstruct volumetric MRI data from non‑aligned scans, enabling the generation of novel view planes that are better aligned with spinal anatomy. These resampled images are then used to predict ordinal severity grades of localized stenosis, outperforming traditional Voxel Interpolation and Cubic B‑spline resampling methods. Across all stenosis conditions, the Gaussian Splatting approach yields more accurate diagnostic gradings than raw or conventionally resampled scans.
EndoPrior-GS is a new pipeline for dynamic endoscopic reconstruction that combines frame-extracted vision heuristics with depth maps. It creates a joint texture prior using a tool-filtered tissue mask, a non-specular photometric filter, and anatomical salience, which guides primitive initialization and density control. Experiments on EndoNeRF and SCARED datasets show that EndoPrior-GS reduces Flow Error by 27.7% and 25.8% compared to representative methods while maintaining real-time rendering speed and competitive quality.
arXiv:2609.24468v2 Announce Type: replace Abstract: Three-dimensional (3D) multi-contrast magnetic resonance imaging (MCMRI) provides rich anatomical and quantitative information but requires long ac...
CAPS is a Clinically‑Verifiable Anatomy‑Prioritized Synthesis framework designed to impute missing MRI modalities for brain tumor segmentation. It uses a hybrid loss (L₁ + L_AFP + L_DualDice) to preserve deep anatomical features and topological boundaries, achieving high synthesis fidelity and robust segmentation (82.38% mean Dice) on the BraTS Adult Glioma dataset. The method also generalizes well to unseen cohorts and has been validated by blinded radiologists, who report improved image quality and clinical utility.
CTBakeGS is a training‑free method that converts computed tomography (CT) volume renderings into three‑dimensional Gaussian splat (3DGS) models. By placing splats on an adaptive octree of millimetre‑sized cells and computing their colour and opacity directly on the graphics processor, the approach achieves photorealistic renderings without the need for scene‑specific training. Conversion takes only a few seconds on a laptop, producing models that render at 68 fps and attain high PSNR values (≈30–33 dB) for bone, vessels, and skin.
RARF is a task‑agnostic, region‑aware rectified flow framework designed for 3D brain MRI inpainting. It limits stochastic interpolation to the inpainting region while keeping observed voxels fixed, using a 3D neural network that processes a partially voided image, Gaussian noise, a mask, and a timestep. The model is trained with masked flow‑matching and reconstruction‑consistency objectives, and during inference it transports noise toward a plausible reconstruction that preserves anatomical consistency, achieving competitive results on the BraTS Inpainting Challenge 2026.