CVSep 9, 2021

IICNet: A Generic Framework for Reversible Image Conversion

arXiv:2109.04242v130 citationsHas Code
Originality Highly original
AI Analysis

This provides a scalable solution for embedding and restoring visual content like short videos, reducing the need for hand-engineered task-specific networks.

The paper tackled the problem of reversible image conversion (RIC) by developing IICNet, a generic framework based on invertible neural networks, which outperformed task-specific methods on existing tasks and generalized well to new ones.

Reversible image conversion (RIC) aims to build a reversible transformation between specific visual content (e.g., short videos) and an embedding image, where the original content can be restored from the embedding when necessary. This work develops Invertible Image Conversion Net (IICNet) as a generic solution to various RIC tasks due to its strong capacity and task-independent design. Unlike previous encoder-decoder based methods, IICNet maintains a highly invertible structure based on invertible neural networks (INNs) to better preserve the information during conversion. We use a relation module and a channel squeeze layer to improve the INN nonlinearity to extract cross-image relations and the network flexibility, respectively. Experimental results demonstrate that IICNet outperforms the specifically-designed methods on existing RIC tasks and can generalize well to various newly-explored tasks. With our generic IICNet, we no longer need to hand-engineer task-specific embedding networks for rapidly occurring visual content. Our source codes are available at: https://github.com/felixcheng97/IICNet.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes