无配对图像到图像翻译的自监督语义桥
Unpaired Image-to-Image Translation via a Self-Supervised Semantic Bridge
AI总结：
本文提出自监督语义桥框架，通过整合外部语义先验实现无配对图像到图像翻译的高保真度，提升医学图像合成效果。
摘要：
对抗扩散和扩散-反转方法在无配对图像到图像翻译方面取得了进展，但每种方法都面临关键限制。对抗方法在训练过程中需要目标域对抗损失，这可能限制其对未见过的数据的泛化能力，而扩散-反转方法常常产生低保真度的翻译，因为反转到噪声-潜在表示不完美。在本工作中，我们提出了自监督语义桥（SSB），一种将外部语义先验整合到扩散桥模型中的通用框架，以实现空间忠实的翻译，而无需跨域监督。我们的核心思想是利用自监督视觉编码器学习对视觉变化具有不变性的表示，但能捕捉几何结构，形成一个共享的潜在空间，该空间条件扩散桥。广泛的实验表明，SSB在挑战性的医学图像合成中，无论是领域内还是领域外设置，都优于强大的先验方法，并且可以轻松扩展到高质量的文本引导编辑。
英文摘要：
Adversarial diffusion and diffusion-inversion methods have advanced unpaired image-to-image translation, but each faces key limitations. Adversarial approaches require target-domain adversarial loss during training, which can limit generalization to unseen data, while diffusion-inversion methods often produce low-fidelity translations due to imperfect inversion into noise-latent representations. In this work, we propose the Self-Supervised Semantic Bridge (SSB), a versatile framework that integrates external semantic priors into diffusion bridge models to enable spatially faithful translation without cross-domain supervision. Our key idea is to leverage self-supervised visual encoders to learn representations that are invariant to appearance changes but capture geometric structure, forming a shared latent space that conditions the diffusion bridges. Extensive experiments show that SSB outperforms strong prior methods for challenging medical image synthesis in both in-domain and out-of-domain settings, and extends easily to high-quality text-guided editing.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
