SynthRGB-T：面向多样性合成的语言-视觉引导图像翻译
SynthRGB-T: Language-Vision Guided Image Translation for Diversity Synthesis
把红外↔可见光图像翻译建模为视觉语言引导的去噪扩散过程，并用解耦注入策略与双条件交叉注意力处理多路引导冲突，可直接复用于跨模态数据增广与开放世界条件生成。
原文依据 we formulate image translation as a vision-language guided denoising diffusion process, enabling flexible conditioning and open-world generalization
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论弥合红外与可见光图像之间的模态鸿沟，对于跨模态理解以及丰富多模态基准至关重要。然而，现有方法仍局限于一对一映射，且通常在单向或闭集场景下进行评估。为应对这一挑战，我们提出 SynthRGB-T，一个面向多样且双向图像翻译的统一框架。具体而言，我们将图像翻译建模为视觉语言引导的去噪扩散过程，从而实现灵活的条件控制与开放世界泛化。为增强语义对齐，我们引入视觉定位流水线（VGP），利用基础模型的世界知识提供细粒度的翻译引导。在扩散过程中，我们提出采用解耦注入策略以缓解多路引导之间的相互干扰。此外，我们设计了双条件交叉注意力（DCCA）模块，以促进潜变量空间中的协同表征学习。SynthRGB-T 简单且通用——能够合成多样、高保真的数据，显著扩展社区内的多模态资源。在多个真实世界基准上的全面评估证实，SynthRGB-T 相较现有方法取得了更优性能并提升了视觉多样性。
英文原文摘要 1341 字符
Bridging the modality gap between infrared and visible imagery is critical for cross-modal understanding and for enriching multimodal benchmarks. However, existing approaches remain confined to one-to-one mappings and are typically evaluated on unidirectional or closed-set scenarios. To address this challenge, we present SynthRGB-T, a unified framework for diverse and bidirectional image translation. Specifically, we formulate image translation as a vision-language guided denoising diffusion process, enabling flexible conditioning and open-world generalization. To enhance semantic alignment, a Visual Grounding Pipeline (VGP) is introduced to exploit the world knowledge of foundation models for fine-grained translation guidance. During the diffusion process, we propose to adopt a decoupling injection strategy to alleviate interference among multiple guidance. In addition, a Dual Conditional Cross-Attention (DCCA) module is designed to facilitate collaborative representation learning in latent space. SynthRGB-T is simple and versatile--capable of synthesizing diverse, high-fidelity data that substantially extends multimodal resources within the community. Comprehensive evaluations on multiple real-world benchmarks confirm that SynthRGB-T delivers superior performance and enhanced visual diversity over existing approaches.