• Corpus ID: 237454617

IICNet: A Generic Framework for Reversible Image Conversion

  title={IICNet: A Generic Framework for Reversible Image Conversion},
  author={Ka Leong Cheng and Yueqi Xie and Qifeng Chen},
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… 
A Compact Neural Network-based Algorithm for Robust Image Watermarking
  • Hong-Bo Xu, Rong Wang, Jia Wei, Shao-Ping Lu
  • Computer Science
  • 2021
A simple but effective bit message normalization module to condense the bit message to be embedded, and a noise layer is designed to simulate various practical attacks under the IWN framework to enhance the robustness of the watermarking solution.


Enhanced Invertible Encoding for Learned Image Compression
This paper proposes an enhanced Invertible Encoding Network with invertible neural networks (INNs) to largely mitigate the information loss problem for better compression, and shows that this method outperforms the existing learned image compression methods and compression standards, including VVC (VTM 12.1), especially for high-resolution images.
Modeling Lost Information in Lossy Image Compression
Experimental results demonstrate that with a new component replacing the auto-encoder in image compression methods, ILC can significantly outperform the baseline method on extensive benchmark datasets by combining with the existing compression algorithms.
Invertible grayscale
This paper proposes to learn and embed the color-encoding scheme via a convolutional neural network (CNN) and encode the original color information into the synthesized grayscale, in a way that users cannot recognize any anomalies.
End-to-end Optimized Image Compression
Across an independent set of test images, it is found that the optimized method generally exhibits better rate-distortion performance than the standard JPEG and JPEG 2000 compression methods, and a dramatic improvement in visual quality is observed, supported by objective quality estimates using MS-SSIM.
Guided Image Generation with Conditional Invertible Neural Networks
This work introduces a new architecture called conditional invertible neural network (cINN), which combines the purely generative INN model with an unconstrained feed-forward network, which efficiently preprocesses the conditioning input into useful features.
Lossy Image Compression with Compressive Autoencoders
It is shown that minimal changes to the loss are sufficient to train deep autoencoders competitive with JPEG 2000 and outperforming recently proposed approaches based on RNNs, and furthermore computationally efficient thanks to a sub-pixel architecture, which makes it suitable for high-resolution images.
Deep Image Matting
A novel deep learning based algorithm that can tackle image matting problems when an image has similar foreground and background colors or complicated textures and evaluation results demonstrate the superiority of this algorithm over previous methods.
Invertible Image Rescaling
An Invertible Rescaling Net (IRN) is developed with deliberately designed framework and objectives to produce visually-pleasing low-resolution images and meanwhile capture the distribution of the lost information using a latent variable following a specified distribution in the downscaling process.
HiDDeN: Hiding Data With Deep Networks
This work finds that neural networks can learn to use invisible perturbations to encode a rich amount of useful information, and demonstrates that adversarial training improves the visual quality of encoded images.
Background Matting: The World Is Your Green Screen
This work proposes a method for creating a matte – the per-pixel foreground color and alpha – of a person by taking photos or videos in an everyday setting with a handheld camera and trains a deep network with an adversarial loss to predict the matte.