Spectral Consistent Flow for One-step 3D Medical Image Translation
2026-07-12 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors introduce SC-Flow, a method for converting 3D medical images from one type to another by modeling the process like a smooth random path. They improve the quality of the images by using a special correction that controls how details change in frequency, helping keep both fine details and overall structure accurate. Their approach is faster because it only needs one main calculation step in a simplified space. Tests on multiple datasets show it produces more accurate and reliable image translations compared to other methods.
3D medical image translationlatent spaceBrownian bridge processmean velocity fieldpower spectral densityfrequency-domain gain modulationanatomical fidelitystructural coherenceimage translationgenerative flow models
Authors
Haoqing Li, Jun Shi, Mingchao Li, Zehua Zhu, Qiwei Jia, Jiong Shi, Hong An
Abstract
We present Spectral Consistent Flow (SC-Flow), a 3D medical image translation framework with a single function evaluation (1-NFE) in the latent space. This approach reformulates medical image translation as a stochastic Brownian bridge process that directly constructs a mapping between source and target modalities by predicting the support regularized mean velocity field. To mitigate modality entanglement, over-smoothing, and artifacts induced by the implicit low-pass modulation of the latent average velocity, we introduce a Spectral Consistency Corrector that dynamically regularizes the evolution of the power spectral density via learnable frequency-domain gain modulation. This mechanism establishes an explicit bridge between spatial textures and spectral energy flow, enabling the model to recover fine-grained anatomical fidelity while maintaining global structural coherence. Extensive experiments on four datasets demonstrate that SC-Flow delivers significantly more accurate, consistent, and robust performance across various translation scenarios.