TIACam: Text-Anchored Invariant Feature Learning with Auto-Augmentation for Camera-Robust Zero-Watermarking
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866917286397345792 |
|---|---|
| author | Tanvir, Abdullah All Dasgupta, Agnibh Zhong, Xin |
| author_facet | Tanvir, Abdullah All Dasgupta, Agnibh Zhong, Xin |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_18863 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | TIACam: Text-Anchored Invariant Feature Learning with Auto-Augmentation for Camera-Robust Zero-Watermarking Tanvir, Abdullah All Dasgupta, Agnibh Zhong, Xin Image and Video Processing Computer Vision and Pattern Recognition Machine Learning Multimedia 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. |
| title | TIACam: Text-Anchored Invariant Feature Learning with Auto-Augmentation for Camera-Robust Zero-Watermarking |
| topic | Image and Video Processing Computer Vision and Pattern Recognition Machine Learning Multimedia |
| url | https://arxiv.org/abs/2602.18863 |