LiFT: Lifted Inter-slice Feature Trajectories for 3D Image Generation from 2D Generators
Quick Take
LiFT introduces a framework for efficient 3D medical image generation using inter-slice feature trajectories.
Key Points
- Factorizes 3D synthesis into per-slice generation.
- Employs tri-planar drifting loss for trajectory alignment.
- Achieves high fidelity with lower computational cost.
📖 Reader Mode
~2 min readAbstract:High-resolution 3D medical image generation remains challenging because fully volumetric models are computationally expensive, while efficient 2D slice generators often fail to preserve anatomical consistency across the third dimension. We propose LiFT, a framework for Lifted inter-slice Feature Trajectories that factorizes 3D volume synthesis into per-slice image generation and inter-slice trajectory learning. Rather than modeling the volumetric distribution end-to-end, LiFT treats a volume as an ordered trajectory in feature space, capturing how anatomical structures appear, transform, and disappear across depth. A tri-planar drifting loss aligns the trajectory of generated slices with the trajectories of real volumes, enabling distributional learning over inter-slice progressions in unconditional generation; in paired translation, a bidirectional $z$-context mixer trained against the registered target supplies through-plane coherence while preserving per-slice fidelity. We evaluate LiFT on BraTS 2023 (unconditional and missing-modality MR) and SynthRAD2023 (MR-to-CT). Across these settings, LiFT preserves per-slice quality, approaches the reported cWDM missing-MR reconstruction quality at $\sim$$135\times$ lower inference cost (without formal equivalence testing), and improves through-plane coherence on MR-to-CT relative to a no-mapper ablation, demonstrating that lightweight inter-slice trajectory learning is a viable route to high-resolution 3D medical synthesis.
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Image and Video Processing (eess.IV) |
| Cite as: | arXiv:2605.19060 [cs.CV] |
| (or arXiv:2605.19060v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2605.19060 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Xinhe Zhang [view email]
[v1]
Mon, 18 May 2026 19:30:19 UTC (24,747 KB)
— Originally published at arxiv.org
More from arXiv cs.CV
See more →GeoSym127K: Scalable Symbolically-verifiable Synthesis for Multimodal Geometric Reasoning
GeoSym127K introduces a scalable neuro-symbolic framework for enhanced geometric reasoning in multimodal models.