TIACam：面向相机鲁棒零水印的文本锚定不变特征学习与自动增强
TIACam: Text-Anchored Invariant Feature Learning with Auto-Augmentation for Camera-Robust Zero-Watermarking
可学习的自动增强器用可微的几何、光度与摩尔纹算子模拟相机重捕获退化，这一思路可直接迁移到任何需要建模真实拍摄退化的鲁棒性训练中；文本锚定的跨模态对抗对齐则为在特征空间约束语义一致性提供了可复用的手段。
原文依据 a learnable auto-augmentor that discovers camera-like distortions through differentiable geometric, photometric, and Moire operators
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论相机重捕获会引入透视畸变、光照变化和摩尔纹干扰等复杂光学退化，这对深度水印系统而言仍是难题。本文提出 TIACam，一个面向相机鲁棒零水印的文本锚定不变特征学习框架，并配备自动增强机制。该方法融合三项关键创新：(1) 可学习的自动增强器，通过可微的几何、光度与摩尔纹算子发现类相机失真；(2) 文本锚定不变特征学习器，通过图像与文本之间的跨模态对抗对齐来强制语义一致性；(3) 零水印检测头，在不修改图像像素的前提下将二进制消息绑定到不变特征空间中。该统一形式联合优化不变性、语义对齐与水印可恢复性。在合成数据与真实相机拍摄数据上的大量实验表明，TIACam 取得了最优的特征稳定性与水印提取准确率，在多模态不变性学习与物理鲁棒零水印之间建立了有原则的桥梁。
英文原文摘要 1159 字符
Camera recapture introduces complex optical degradations, such as perspective warping, illumination shifts, and Moire interference, that remain challenging for deep watermarking systems. We present TIACam, a text-anchored invariant feature learning framework with auto-augmentation for camera-robust zero-watermarking. The method integrates three key innovations: (1) a learnable auto-augmentor that discovers camera-like distortions through differentiable geometric, photometric, and Moire operators; (2) a text-anchored invariant feature learner that enforces semantic consistency via cross-modal adversarial alignment between image and text; and (3) a zero-watermarking head that binds binary messages in the invariant feature space without modifying image pixels. This unified formulation jointly optimizes invariance, semantic alignment, and watermark recoverability. Extensive experiments on both synthetic and real-world camera captures demonstrate that TIACam achieves state-of-the-art feature stability and watermark extraction accuracy, establishing a principled bridge between multimodal invariance learning and physically robust zero-watermarking.