TIACam: Text-Anchored Invariant Feature Learning with Auto-Augmentation for Camera-Robust Zero-Watermarking

TL;DR

TIACam introduces a novel framework combining auto-augmentation, text-anchored invariant features, and zero-watermarking to enhance camera-robustness in digital watermarking, effectively handling complex optical degradations.

Contribution

The paper proposes a unified approach integrating learnable augmentation, cross-modal semantic alignment, and zero-watermarking for improved camera-robust digital watermarking.

Findings

Achieves state-of-the-art stability in feature extraction under camera distortions.

Demonstrates high accuracy in watermark recovery on real-world camera captures.

Establishes a new benchmark for camera-robust zero-watermarking methods.

Abstract

Camera recapture introduces complex optical degradations, such as perspective warping, illumination shifts, and Moir\'e 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 Moir\'e 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.