用文本引导的自适应增强，让水印更抗相机干扰。
TIACam: Text-Anchored Invariant Feature Learning with Auto-Augmentation for Camera-Robust Zero-Watermarking
- 通过可学习的自动增强器模拟相机畸变
- 在不变特征空间中实现高精度水印提取
- 适合需要真实相机鲁棒性的数字版权保护场景
相机重拍引入了复杂的光学退化，如透视扭曲、光照变化和摩尔纹干扰，对深度水印系统仍是挑战。本文提出TIACam，一种文本锚定的不变特征学习框架，结合自动增强技术，实现抗相机干扰的零水印。方法包含三项创新：(1) 可学习的自动增强器，通过可微分的几何、光度和摩尔纹算子发现相机类失真；(2) 文本锚定的不变特征学习器，通过图像与文本间的跨模态对抗对齐保证语义一致性；(3) 零水印头，在不变特征空间中嵌入二进制信息，不修改像素。该统一框架联合优化不变性、语义对齐与水印可恢复性。在合成与真实相机拍摄数据上广泛实验表明，TIACam在特征稳定性与水印提取准确率方面达到当前最优，建立多模态不变性学习与物理鲁棒零水印之间的原则性桥梁。
原文摘要 · Abstract (English)
Camera recapture introduces complex optical degradations, such as perspective warping, illumination shifts, and Moiré 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 Moiré 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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。