医学影像单切片转3D重建仍难，现有模型普遍失败但SAM3D表现最好
Single-Slice-to-3D Reconstruction in Medical Imaging and Natural Objects: A Comparative Benchmark with SAM 3D
- 用五个主流3D生成模型对比单切片输入的重建效果
- 所有模型在医学数据上体素重合率均很低，显示深度歧义根本性挑战
- SAM3D最接近真实解剖结构，适合需保留拓扑关系的医疗应用
三维成像对临床诊断至关重要，但成本高、耗时长，促使研究者利用基于自然图像训练的图像到3D基础模型，从二维模态推断三维体积。然而，这些模型在自然图像上学习的几何先验难以迁移到本质平面的医学数据。在六个医学和两个自然数据集上对五种先进模型（SAM3D、Hunyuan3D-2.1、Direct3D、Hi3DGen、TripoSG）的基准测试表明，由于单切片输入带来的严重深度歧义，所有方法的体素重合率均保持低位。尽管存在根本性体积重建失败，全局距离指标显示SAM3D最能捕捉与真实医学形状的拓扑相似性，而其他模型易出现过度简化。最终结果量化了零样本单切片3D推断的局限性，强调可靠医学3D重建需领域特异性适配与解剖约束以克服复杂医学几何结构。
原文摘要 · Abstract (English)
While three-dimensional imaging is essential for clinical diagnosis, its high cost and long wait times have motivated the use of image-to-3D foundation models to infer volume from two-dimensional modalities. However, because these models are trained on natural images, their learned geometric priors struggle to transfer to inherently planar medical data. A benchmark of five state-of-the-art models (SAM3D, Hunyuan3D-2.1, Direct3D, Hi3DGen, and TripoSG) across six medical and two natural datasets revealed that voxel-based overlap remains uniformly low across all methods due to severe depth ambiguity from single-slice inputs. Despite this fundamental volumetric failure, global distance metrics indicate that SAM3D best captures topological similarity to ground-truth medical shapes, whereas alternative models are prone to oversimplification. Ultimately, these findings quantify the limits of zero-shot single-slice 3D inference, highlighting that reliable medical 3D reconstruction requires domain-specific adaptation and anatomical constraints to overcome complex medical geometries.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。