Towards Unified Semantic and Controllable Image Fusion: A Diffusion Transformer Approach

• URL: http://arxiv.org/abs/2512.07170v1
• Date: Mon, 08 Dec 2025 05:04:54 GMT
• Title: Towards Unified Semantic and Controllable Image Fusion: A Diffusion Transformer Approach
• Authors: Jiayang Li, Chengjie Jiang, Junjun Jiang, Pengwei Liang, Jiayi Ma, Liqiang Nie,
• Abstract summary: DiTFuse is an instruction-driven framework that performs semantics-aware fusion within a single model.<n>Experiments on public IVIF, MFF, and MEF benchmarks confirm superior quantitative and qualitative performance, sharper textures, and better semantic retention.
• Score: 99.80480649258557
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Image fusion aims to blend complementary information from multiple sensing modalities, yet existing approaches remain limited in robustness, adaptability, and controllability. Most current fusion networks are tailored to specific tasks and lack the ability to flexibly incorporate user intent, especially in complex scenarios involving low-light degradation, color shifts, or exposure imbalance. Moreover, the absence of ground-truth fused images and the small scale of existing datasets make it difficult to train an end-to-end model that simultaneously understands high-level semantics and performs fine-grained multimodal alignment. We therefore present DiTFuse, instruction-driven Diffusion-Transformer (DiT) framework that performs end-to-end, semantics-aware fusion within a single model. By jointly encoding two images and natural-language instructions in a shared latent space, DiTFuse enables hierarchical and fine-grained control over fusion dynamics, overcoming the limitations of pre-fusion and post-fusion pipelines that struggle to inject high-level semantics. The training phase employs a multi-degradation masked-image modeling strategy, so the network jointly learns cross-modal alignment, modality-invariant restoration, and task-aware feature selection without relying on ground truth images. A curated, multi-granularity instruction dataset further equips the model with interactive fusion capabilities. DiTFuse unifies infrared-visible, multi-focus, and multi-exposure fusion-as well as text-controlled refinement and downstream tasks-within a single architecture. Experiments on public IVIF, MFF, and MEF benchmarks confirm superior quantitative and qualitative performance, sharper textures, and better semantic retention. The model also supports multi-level user control and zero-shot generalization to other multi-image fusion scenarios, including instruction-conditioned segmentation.

Related papers

• CtrlFuse: Mask-Prompt Guided Controllable Infrared and Visible Image Fusion [51.060328159429154]
  Infrared and visible image fusion generates all-weather perception-capable images by combining complementary modalities.<n>We propose CtrlFuse, a controllable image fusion framework that enables interactive dynamic fusion guided by mask prompts.<n> Experiments demonstrate state-of-the-art results in both fusion controllability and segmentation accuracy, with the adapted task branch even outperforming the original segmentation model.
  arXiv  Detail & Related papers  (2026-01-12T13:36:48Z)
• FusionFM: All-in-One Multi-Modal Image Fusion with Flow Matching [42.22268167379098]
  We formulate image fusion as a direct probabilistic transport from source modalities to the fused image distribution.<n>We employ a task-aware selection function to select the most reliable pseudo-labels for each task.<n>For multi-task scenarios, we integrate elastic weight consolidation and experience replay mechanisms to preserve cross-task performance.
  arXiv  Detail & Related papers  (2025-11-17T02:56:48Z)
• UniAlignment: Semantic Alignment for Unified Image Generation, Understanding, Manipulation and Perception [54.53657134205492]
  UniAlignment is a unified multimodal generation framework within a single diffusion transformer.<n>It incorporates both intrinsic-modal semantic alignment and cross-modal semantic alignment, thereby enhancing the model's cross-modal consistency and instruction-following robustness.<n>We present SemGen-Bench, a new benchmark specifically designed to evaluate multimodal semantic consistency under complex textual instructions.
  arXiv  Detail & Related papers  (2025-09-28T09:11:30Z)
• Efficient Rectified Flow for Image Fusion [48.330480065862474]
  We propose RFfusion, an efficient one-step diffusion model for image fusion based on Rectified Flow.<n>We also propose a task-specific variational autoencoder architecture tailored for image fusion.<n>Our method outperforms other state-of-the-art methods in terms of both inference speed and fusion quality.
  arXiv  Detail & Related papers  (2025-09-20T06:21:00Z)
• MAFS: Masked Autoencoder for Infrared-Visible Image Fusion and Semantic Segmentation [43.62940654606311]
  We propose a unified network for image fusion and semantic segmentation.<n>We devise a heterogeneous feature fusion strategy to enhance semantic-aware capabilities for image fusion.<n>Within the framework, we design a novel multi-stage Transformer decoder to aggregate fine-grained multi-scale fused features efficiently.
  arXiv  Detail & Related papers  (2025-09-15T11:55:55Z)
• Fusion from Decomposition: A Self-Supervised Approach for Image Fusion and Beyond [74.96466744512992]
  The essence of image fusion is to integrate complementary information from source images. DeFusion++ produces versatile fused representations that can enhance the quality of image fusion and the effectiveness of downstream high-level vision tasks.
  arXiv  Detail & Related papers  (2024-10-16T06:28:49Z)
• A Task-guided, Implicitly-searched and Meta-initialized Deep Model for Image Fusion [69.10255211811007]
  We present a Task-guided, Implicit-searched and Meta- generalizationd (TIM) deep model to address the image fusion problem in a challenging real-world scenario. Specifically, we propose a constrained strategy to incorporate information from downstream tasks to guide the unsupervised learning process of image fusion. Within this framework, we then design an implicit search scheme to automatically discover compact architectures for our fusion model with high efficiency.
  arXiv  Detail & Related papers  (2023-05-25T08:54:08Z)
• Equivariant Multi-Modality Image Fusion [124.11300001864579]
  We propose the Equivariant Multi-Modality imAge fusion paradigm for end-to-end self-supervised learning. Our approach is rooted in the prior knowledge that natural imaging responses are equivariant to certain transformations. Experiments confirm that EMMA yields high-quality fusion results for infrared-visible and medical images.
  arXiv  Detail & Related papers  (2023-05-19T05:50:24Z)
• TransFuse: A Unified Transformer-based Image Fusion Framework using Self-supervised Learning [5.849513679510834]
  Image fusion is a technique to integrate information from multiple source images with complementary information to improve the richness of a single image. Two-stage methods avoid the need of large amount of task-specific training data by training encoder-decoder network on large natural image datasets. We propose a destruction-reconstruction based self-supervised training scheme to encourage the network to learn task-specific features.
  arXiv  Detail & Related papers  (2022-01-19T07:30:44Z)

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.