Tackling Ill-posedness of Reversible Image Conversion with Well-posed Invertible Network
Preprint
Abstract
Reversible image conversion (RIC) suffers from ill-posedness issues due to its forward conversion process being considered an underdetermined system. Despite employing invertible neural networks (INN), existing RIC methods intrinsically remain ill-posed as inevitably introducing uncertainty by incorporating randomly sampled variables. To tackle the ill-posedness dilemma, we focus on developing a reliable approximate left inverse for the underdetermined system by constructing an overdetermined system with a non-zero Gram determinant, thus ensuring a well-posed solution. Based on this principle, we propose a well-posed invertible $1\times1$ convolution (WIC), which eliminates the reliance on random variable sampling and enables the development of well-posed invertible networks. Furthermore, we design two innovative networks, WIN-Naïve and WIN, with the latter incorporating advanced skip-connections to enhance long-term memory. Our methods are evaluated across diverse RIC tasks, including reversible image hiding, image rescaling, and image decolorization, consistently achieving state-of-the-art performance. Extensive experiments validate the effectiveness of our approach, demonstrating its ability to overcome the bottlenecks of existing RIC solutions and setting a new benchmark in the field. Codes are available in https://github.com/BNU-ERC-ITEA/WIN.
Keywords
All Related Versions
This publication has 33 references indexed in Scilit:
- Diffusion-Based Hierarchical Image Steganography2025
- CD-iNet: Deep Invertible Network for Perceptual Image Color Difference MeasurementInternational Journal of Computer Vision, 2024
- Invertible Rescaling Network and Its ExtensionsInternational Journal of Computer Vision, 2022
- Invertible Image DecolorizationIEEE Transactions on Image Processing, 2021
- Interpretable Detail-Fidelity Attention Network for Single Image Super-ResolutionIEEE Transactions on Image Processing, 2021
- Learned Image Downscaling for Upscaling Using Content Adaptive ResamplerIEEE Transactions on Image Processing, 2020
- Color Contrast-Preserving DecolorizationIEEE Transactions on Image Processing, 2018
- Inverse problems with Poisson data: statistical regularization theory, applications and algorithmsInverse Problems, 2016
- Antialiasing Filter Design for Subpixel Downsampling via Frequency-Domain AnalysisIEEE Transactions on Image Processing, 2011
- Multispectral image visualization through first-order fusionIEEE Transactions on Image Processing, 2002