Tackling Ill-posedness of Reversible Image Conversion with Well-posed Invertible Network

TL;DR

This paper introduces a well-posed invertible network approach for reversible image conversion, overcoming ill-posedness issues by constructing an overdetermined system, leading to state-of-the-art results across multiple tasks.

Contribution

The paper proposes a novel well-posed invertible convolution and networks that eliminate reliance on random sampling, improving the stability and performance of reversible image conversion.

Findings

Achieves state-of-the-art performance in various RIC tasks.

Effectively overcomes ill-posedness in reversible image conversion.

Demonstrates robustness and improved stability of the proposed networks.

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-Na\"ive 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.