# Single-Slice-to-3D Reconstruction in Medical Imaging and Natural Objects: A Comparative Benchmark with SAM 3D

arXiv: https://arxiv.org/abs/2602.09407 · HTML: https://mlsanity.com/paper/2602.09407/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 33 references that are in the map.
- First posted on arXiv 10 Feb 2026.

## Builds on (most cited first, 18 of 18)

- [The Medical Segmentation Decathlon](https://mlsanity.com/paper/2106.05735/) (2021)
- [Google Scanned Objects: A High-Quality Dataset of 3D Scanned Household Items](https://mlsanity.com/paper/2204.11918/) (2022)
- [Domain Adaptation for Medical Image Analysis: A Survey](https://mlsanity.com/paper/2102.09508/) (2021)
- [What Do Single-view 3D Reconstruction Networks Learn?](https://mlsanity.com/paper/1905.03678/) (2019)
- [SAM 3D: 3Dfy Anything in Images](https://mlsanity.com/paper/2511.16624/) (2025)
- [TripoSG: High-Fidelity 3D Shape Synthesis using Large-Scale Rectified Flow Models](https://mlsanity.com/paper/2502.06608/) (2025)
- [Direct3D: Scalable Image-to-3D Generation via 3D Latent Diffusion Transformer](https://mlsanity.com/paper/2405.14832/) (2024)
- [Hunyuan3D 2.1: From Images to High-Fidelity 3D Assets with Production-Ready PBR Material](https://mlsanity.com/paper/2506.15442/) (2025)
- [Hi3DGen: High-fidelity 3D Geometry Generation from Images via Normal Bridging](https://mlsanity.com/paper/2503.22236/) (2025)
- [X2CT-GAN: Reconstructing CT from Biplanar X-Rays with Generative Adversarial Networks](https://mlsanity.com/paper/1905.06902/) (2019)
- [Learning Shape Priors for Single-View 3D Completion and Reconstruction](https://mlsanity.com/paper/1809.05068/) (2018)
- [Surgical-DINO: Adapter Learning of Foundation Models for Depth Estimation in Endoscopic Surgery](https://mlsanity.com/paper/2401.06013/) (2024)
- [Learning single-image 3D reconstruction by generative modelling of shape, pose and shading](https://mlsanity.com/paper/1901.06447/) (2019)
- [Deep Learning Based Brain Tumor Segmentation: A Survey](https://mlsanity.com/paper/2007.09479/) (2020)
- [DepthCues: Evaluating Monocular Depth Perception in Large Vision Models](https://mlsanity.com/paper/2411.17385/) (2024)
- [AeroPath: An airway segmentation benchmark dataset with challenging pathology](https://mlsanity.com/paper/2311.01138/) (2023)
- [X-Diffusion: Generating Detailed 3D MRI Volumes From a Single Image Using Cross-Sectional Diffusion Models](https://mlsanity.com/paper/2404.19604/) (2024)
- [Cue3D: Quantifying the Role of Image Cues in Single-Image 3D Generation](https://mlsanity.com/paper/2511.22121/) (2025)

## Abstract (arXiv)

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.