UniFusion：兼具鲁棒表征与源感知保持的统一图像融合框架
UniFusion: A Unified Image Fusion Framework with Robust Representation and Source-Aware Preservation
用 DINOv3 冻结特征构建跨模态共享语义空间，并用重建-对齐损失约束融合输出与各源图的一致性，这套「基础模型特征 + 重建约束」的组合可直接迁移到多曝光/多聚焦/红外-可见光等任意多源融合与复原任务，双层优化解耦融合与重建目标的思路也适用于其他多目标耦合的低层视觉训练。
原文依据 leveraging DINOv3 for modality-consistent feature extraction, UniFusion establishes a shared semantic space for diverse inputs
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论图像融合旨在整合多幅源图像中的互补信息，从而产生信息更丰富、视觉更一致的表示，既有利于人类感知，也有益于下游视觉任务。尽管近期取得了进展，但现有大多数融合方法都是针对特定任务（即多模态融合、多曝光融合或多聚焦融合）设计的，并且在融合过程中难以有效保持源信息。这一局限主要源于任务特定的架构以及深层传播所导致的源信息退化。为克服这些问题，我们提出 UniFusion，一个旨在实现跨任务泛化的统一图像融合框架。首先，UniFusion 利用 DINOv3 进行模态一致的特征提取，为多样化的输入建立共享语义空间。其次，为保持对每幅源图像的理解，我们引入重建对齐损失，以维持融合输出与输入之间的一致性。最后，我们采用双层优化策略来解耦并联合优化重建目标与融合目标，有效平衡二者之间的耦合关系并确保平滑收敛。在多个融合任务上的大量实验表明，UniFusion 具有更优的视觉质量、泛化能力以及对真实场景的适应性。
英文原文摘要 1383 字符
Image fusion aims to integrate complementary information from multiple source images to produce a more informative and visually consistent representation, benefiting both human perception and downstream vision tasks. Despite recent progress, most existing fusion methods are designed for specific tasks (i.e., multi-modal, multi-exposure, or multi-focus fusion) and struggle to effectively preserve source information during the fusion process. This limitation primarily arises from task-specific architectures and the degradation of source information caused by deep-layer propagation. To overcome these issues, we propose UniFusion, a unified image fusion framework designed to achieve cross-task generalization. First, leveraging DINOv3 for modality-consistent feature extraction, UniFusion establishes a shared semantic space for diverse inputs. Second, to preserve the understanding of each source image, we introduce a reconstruction-alignment loss to maintain consistency between fused outputs and inputs. Finally, we employ a bilevel optimization strategy to decouple and jointly optimize reconstruction and fusion objectives, effectively balancing their coupling relationship and ensuring smooth convergence. Extensive experiments across multiple fusion tasks demonstrate UniFusion's superior visual quality, generalization ability, and adaptability to real-world scenarios.