arXiv:2606. 24433v1 Announce Type: cross Abstract: Medical point cloud completion is important for anatomical reconstruction and downstream clinical workflows, yet generative modeling in this setting remains insufficiently studied.
Medical point cloud completion is important for anatomical reconstruction and downstream clinical workflows, yet generative modeling in this setting remains insufficiently studied. We investigate completion through continuous-time generative modeling and introduce PCFM, a PTv3-backed flow matching approach for medical point cloud completion.
The paper introduces a high‑resolution Rectified Flow Matching model trained on 256×256 chest CT images to serve as a generative prior for CT reconstruction. A two‑stage training strategy—initial strong anatomically informed augmentation followed by fine‑tuning—helps mitigate overfitting and improve structural fidelity. When evaluated on various CT inverse problems, Flow Matching‑based reconstruction methods outperform diffusion‑based algorithms in PSNR, SSIM, and perceptual quality while requiring fewer sampling steps.
UBone3D is a new framework that completes 3D anatomical shapes from partial ultrasound point clouds using physics-rectified conditional flow matching. It models ultrasound artifacts with a simulated physics proxy and applies test-time physics rectification to guide the completion. The method combines a CT-trained generative shape prior and a physics consistency network, achieving higher reconstruction accuracy and anatomical fidelity than existing baselines.
arXiv:2606. 13188v1 Announce Type: cross Abstract: Building patient-specific cardiac models sits at the heart of precision cardiology, yet getting those models into clinical use keeps running into the same wall: mesh generation is slow, messy, and frustrating.
The paper introduces MedPCFM‑TED, a one‑step distillation framework that uses teacher‑guided endpoint supervision and geometric matching losses to generate cranial implants from point clouds. It outperforms existing one‑step methods on the SkullBreak benchmark, remains competitive on SkullFix, and achieves a generation time of about 0.04 s per sample. The approach demonstrates that rapid, high‑quality implant generation is possible without multiple neural evaluations during inference.
arXiv:2603. 00205v2 Announce Type: replace-cross Abstract: Generative models, particularly Diffusion Models (DM), have shown strong potential for Computed Tomography (CT) reconstruction serving as expressive priors for solving ill-posed inverse problems.
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.
arXiv:2608.24422v1 Announce Type: new Abstract: Recovering the full 3D spine anatomy from intraoperative ultrasound is an ill-posed inverse problem, as the complete structure must be inferred from in...
The paper investigates test‑time adaptation (TTA) techniques for 3D point‑cloud registration in laparoscopic surgery, where synthetic training data must be adapted to noisy, sparse, and occluded real intraoperative reconstructions. It adapts three families of TTA methods—model, normalization, and input adaptation—to handle asymmetric shifts between preoperative meshes and intraoperative clouds, replacing classification‑based entropy objectives with correspondence‑based ones. Experiments on synthetic and real targets show that input adaptation consistently reduces registration error with low inference latency, making it the most promising approach for surgical applications.
arXiv:2606. 24180v1 Announce Type: cross Abstract: Three-dimensional scene completion has evolved as a major problem in computer vision and robotics, and its applications are diverse, including autonomous navigation and augmented reality.
arXiv:2509. 21913v2 Announce Type: replace-cross Abstract: Background: Cone-beam computed tomography CBCT is a commonly used modality for image guided radiotherapy.
Three-dimensional scene completion has evolved as a major problem in computer vision and robotics, and its applications are diverse, including autonomous navigation and augmented reality. In this study, a systematic review has been conducted to compile the research contributions made in the last ten years, i.