InvVis: Large-Scale Data Embedding for Invertible Visualization

TL;DR

InvVis introduces a novel invertible visualization technique that embeds large amounts of data into images, allowing for high-capacity data concealment and accurate reconstruction using invertible neural networks.

Contribution

The paper presents InvVis, a new method for large-capacity data embedding in visualizations with invertibility, enabling data reconstruction and modification from images.

Findings

High data embedding capacity demonstrated

Accurate data restoration achieved

Perceptually indistinguishable images maintained

Abstract

We present InvVis, a new approach for invertible visualization, which is reconstructing or further modifying a visualization from an image. InvVis allows the embedding of a significant amount of data, such as chart data, chart information, source code, etc., into visualization images. The encoded image is perceptually indistinguishable from the original one. We propose a new method to efficiently express chart data in the form of images, enabling large-capacity data embedding. We also outline a model based on the invertible neural network to achieve high-quality data concealing and revealing. We explore and implement a variety of application scenarios of InvVis. Additionally, we conduct a series of evaluation experiments to assess our method from multiple perspectives, including data embedding quality, data restoration accuracy, data encoding capacity, etc. The result of our experiments demonstrates the great potential of InvVis in invertible visualization.