# Efficient Cross-Scale Invertible Hiding Network with Spatial-Frequency Collaboration and Non-Invertible Mechanism

arXiv: https://arxiv.org/abs/2606.25547 · HTML: https://mlsanity.com/paper/2606.25547/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 28 references that are in the map.
- First posted on arXiv 24 Jun 2026.

## Builds on (most cited first, 11 of 11)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Density estimation using Real NVP](https://mlsanity.com/paper/1605.08803/) (2016)
- [Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network](https://mlsanity.com/paper/1609.05158/) (2016)
- [NICE: Non-linear Independent Components Estimation](https://mlsanity.com/paper/1410.8516/) (2014)
- [ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks](https://mlsanity.com/paper/1910.03151/) (2019)
- [SA-Net: Shuffle Attention for Deep Convolutional Neural Networks](https://mlsanity.com/paper/2102.00240/) (2021)
- [MDCN: Multi-scale Dense Cross Network for Image Super-Resolution](https://mlsanity.com/paper/2008.13084/) (2020)
- [Universal Deep Network for Steganalysis of Color Image based on Channel Representation](https://mlsanity.com/paper/2111.12231/) (2021)
- [Improving Cost Learning for JPEG Steganography by Exploiting JPEG Domain Knowledge](https://mlsanity.com/paper/2105.03867/) (2021)

## Abstract (arXiv)

Image hiding aims to conceal image-level messages within cover images at the same resolution. Invertible neural networks (INN)-based image hiding has emerged as an important branch. It treats concealing and revealing as a pair of inverse problems on image domain transformation and uses INN's forward and backward processes to address them. Due to architectural constraints, existing INN-based methods suffer from single-scale and single-domain feature extraction and limited nonlinear representation capability, resulting in inferior image quality. To mitigate these limitations, we propose an efficient cross-scale invertible hiding network with the spatial-frequency collaboration and the non-invertible mechanism, termed CrosInv. CrosInv exploits cross-scale and spatial-frequency collaborative features while enhancing nonlinear representation. Specifically, we introduce a cross-scale invertible module that bijectively maps inputs to cross-scale representations. To effectively integrate spatial and frequency information, the cross-scale invertible module employs pixel shuffle, Haar wavelet transformation, and their inverse operations for scale transformation. Furthermore, a non-invertible cross dense module is integrated to enhance the nonlinearity. Comprehensive experiments verify the effectiveness and superiority of the proposed CrosInv.