Breaking the Resolution Barrier: Arbitrary-resolution Deep Image Steganography Framework

2026-01-22

AI Summary

This work addresses the limitation of existing deep image steganography methods, which assume identical resolutions between cover and secret images, thereby hindering high-fidelity blind recovery across varying resolutions. To overcome this, we propose ARDIS, a novel framework that, for the first time, enables steganographic embedding and reconstruction of secret images at arbitrary resolutions. ARDIS employs a frequency-domain decoupling architecture to separate resolution-dependent global bases from resolution-agnostic high-frequency latent codes. Combined with implicit neural representations and a latent-guided continuous signal reconstruction mechanism, it achieves precise recovery of original details. Experiments demonstrate that ARDIS significantly outperforms state-of-the-art methods in both imperceptibility and cross-resolution reconstruction fidelity, while also supporting blind extraction even when the secret image’s resolution is unknown.

Technology Category

• Computer Vision: Representation Learning for Vision
• Machine Learning: Deep Generative Models & Autoencoders
• Search and Optimization: Mixed Discrete/Continuous Search

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Security and Privacy: Large-scale security measurements
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Deep image steganography (DIS) has achieved significant results in capacity and invisibility. However, current paradigms enforce the secret image to maintain the same resolution as the cover image during hiding and revealing. This leads to two challenges: secret images with inconsistent resolutions must undergo resampling beforehand which results in detail loss during recovery, and the secret image cannot be recovered to its original resolution when the resolution value is unknown. To address these, we propose ARDIS, the first Arbitrary Resolution DIS framework, which shifts the paradigm from discrete mapping to reference-guided continuous signal reconstruction. Specifically, to minimize the detail loss caused by resolution mismatch, we first design a Frequency Decoupling Architecture in hiding stage. It disentangles the secret into a resolution-aligned global basis and a resolution-agnostic high-frequency latent to hide in a fixed-resolution cover. Second, for recovery, we propose a Latent-Guided Implicit Reconstructor to perform deterministic restoration. The recovered detail latent code modulates a continuous implicit function to accurately query and render high-frequency residuals onto the recovered global basis, ensuring faithful restoration of original details. Furthermore, to achieve blind recovery, we introduce an Implicit Resolution Coding strategy. By transforming discrete resolution values into dense feature maps and hiding them in the redundant space of the feature domain, the reconstructor can correctly decode the secret's resolution directly from the steganographic representation. Experimental results demonstrate that ARDIS significantly outperforms state-of-the-art methods in both invisibility and cross-resolution recovery fidelity.

Problem

• deep image steganography
• arbitrary resolution
• resolution mismatch
• blind recovery
• cross-resolution recovery

Innovation

• Arbitrary-resolution
• Deep Image Steganography
• Frequency Decoupling
• Implicit Reconstruction
• Blind Recovery