Compositional Cross-Modality Translation via Whole-Volume Multitask Latent Flow Matching

• URL: http://arxiv.org/abs/2608.08135v1
• Date: Sat, 08 Aug 2026 13:43:23 GMT
• Title: Compositional Cross-Modality Translation via Whole-Volume Multitask Latent Flow Matching
• Abstract summary: Cross-modality medical image translation can reduce the burden of multi-modal acquisitions.<n> Methods operate on 2D slices or 3D patches rather than whole volumes, and train a separate model for each translation task.<n>We propose to decouple these objectives by using a large-scale pretrained 3D variational autoencoder.
• Score: 1.447808799346751
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Cross-modality medical image translation can reduce the burden of multi-modal acquisitions, yet the field remains constrained by two coupled limitations: methods operate on 2D slices or 3D patches rather than whole volumes, and train a separate model for each translation task. Both stem from a single cause, the absence of a sufficiently strong volumetric prior, which forces generative models to learn anatomical appearance and cross-modality mapping simultaneously, an ill-posed problem at the scale of available paired datasets. We propose to decouple these objectives. A large-scale pretrained 3D variational autoencoder provides a compact latent representation of volumetric appearance, reducing translation to a conditional flow-matching problem. This compression makes whole-volume processing tractable, while a resolution-aware sampling strategy preserves native anatomical scale. We train a single model jointly across inter-modality (MRI$\to$CT, CBCT$\to$CT) and intra-modality (MRI$\to$MRI) tasks over three multi-center datasets. Across all tasks, whole-volume processing outperforms its patch-based counterpart, and the multi-task model matches task-specific baselines while replacing $N$ networks with one. Crucially, joint training unlocks capabilities inaccessible to task-specific approaches: zero-shot generalization to anatomical regions unseen during training, within 0.15 SSIM of the fully supervised model, and compositional cross-dataset translation along paths never directly supervised. These results suggest that combining a strong volumetric prior with multitask training is a scalable route toward synthesis systems that generalize beyond their training distribution. Code is available at https://github.com/arco-group/Whole-Volume-Latent-FM.

Related papers

• AdaSurvMamba: Dynamic Fusion and Semantic Scanning for Multimodal Survival Analysis [57.942670844512016]
  We introduce AdaSurvMamba as a novel adaptive framework for multimodal survival analysis.<n>The framework features a Dual-Scale Importance-Aware Reconstruction (DSIR) module to dynamically modulate cross-modal interaction strength.<n>Experiments across five TCGA cohorts demonstrate consistent gains over existing methods.
  arXiv  Detail & Related papers  (2026-06-28T11:36:31Z)
• 3D-Aware Multi-Task Learning with Cross-View Correlations for Dense Scene Understanding [18.76513756741288]
  Current approaches mainly capture cross-task relations in the 2D image space, often leading to unstructured features lacking 3D-awareness.<n>We propose to address this problem by integrating correlations across views, i.e., cost volume, as geometric consistency in the MTL network.<n> Specifically, we introduce a lightweight Cross-view Module (CvM), shared across tasks, to exchange information across views and capture cross-view correlations.
  arXiv  Detail & Related papers  (2025-11-25T18:59:34Z)
• Multi-modal Relation Distillation for Unified 3D Representation Learning [30.942281325891226]
  Multi-modal Relation Distillation (MRD) is a tri-modal pre-training framework designed to distill reputable large Vision-Language Models (VLM) into 3D backbones. MRD aims to capture both intra-relations within each modality as well as cross-relations between different modalities and produce more discriminative 3D shape representations.
  arXiv  Detail & Related papers  (2024-07-19T03:43:48Z)
• MIS-FM: 3D Medical Image Segmentation using Foundation Models Pretrained on a Large-Scale Unannotated Dataset [14.823114726604853]
  We propose a novel self-supervised learning strategy named Volume Fusion (VF) for pretraining 3D segmentation models. VF forces the model to predict the fusion coefficient of each voxel, which is formulated as a self-supervised segmentation task without manual annotations. experiments with different downstream segmentation targets including head and neck organs, thoracic/abdominal organs showed that our pretrained model largely outperformed training from scratch.
  arXiv  Detail & Related papers  (2023-06-29T13:22:13Z)
• Training Transitive and Commutative Multimodal Transformers with LoReTTa [2.5257466288614343]
  We introduce LoReTTa (Linking mOdalities with a tRansitive and commutativE pre-Training sTrAtegy) to address this understudied problem. Our self-supervised framework unifies causal modeling and masked modeling with the rules of commutativity and transitivity. We show that a transformer pre-trained with LoReTTa can handle any mixture of modalities at inference time, including the never-seen pair (A, C) and the triplet (A, B, C)
  arXiv  Detail & Related papers  (2023-05-23T16:58:55Z)
• Multi-scale Transformer Network with Edge-aware Pre-training for Cross-Modality MR Image Synthesis [52.41439725865149]
  Cross-modality magnetic resonance (MR) image synthesis can be used to generate missing modalities from given ones. Existing (supervised learning) methods often require a large number of paired multi-modal data to train an effective synthesis model. We propose a Multi-scale Transformer Network (MT-Net) with edge-aware pre-training for cross-modality MR image synthesis.
  arXiv  Detail & Related papers  (2022-12-02T11:40:40Z)
• Dual Multi-scale Mean Teacher Network for Semi-supervised Infection Segmentation in Chest CT Volume for COVID-19 [76.51091445670596]
  Automated detecting lung infections from computed tomography (CT) data plays an important role for combating COVID-19. Most current COVID-19 infection segmentation methods mainly relied on 2D CT images, which lack 3D sequential constraint. Existing 3D CT segmentation methods focus on single-scale representations, which do not achieve the multiple level receptive field sizes on 3D volume.
  arXiv  Detail & Related papers  (2022-11-10T13:11:21Z)
• On Optimizing the Communication of Model Parallelism [74.15423270435949]
  We study a novel and important communication pattern in large-scale model-parallel deep learning (DL) In cross-mesh resharding, a sharded tensor needs to be sent from a source device mesh to a destination device mesh. We propose two contributions to address cross-mesh resharding: an efficient broadcast-based communication system, and an "overlapping-friendly" pipeline schedule.
  arXiv  Detail & Related papers  (2022-11-10T03:56:48Z)
• M2Net: Multi-modal Multi-channel Network for Overall Survival Time Prediction of Brain Tumor Patients [151.4352001822956]
  Early and accurate prediction of overall survival (OS) time can help to obtain better treatment planning for brain tumor patients. Existing prediction methods rely on radiomic features at the local lesion area of a magnetic resonance (MR) volume. We propose an end-to-end OS time prediction model; namely, Multi-modal Multi-channel Network (M2Net)
  arXiv  Detail & Related papers  (2020-06-01T05:21:37Z)
• Unpaired Multi-modal Segmentation via Knowledge Distillation [77.39798870702174]
  We propose a novel learning scheme for unpaired cross-modality image segmentation. In our method, we heavily reuse network parameters, by sharing all convolutional kernels across CT and MRI. We have extensively validated our approach on two multi-class segmentation problems.
  arXiv  Detail & Related papers  (2020-01-06T20:03:17Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.