Blind Image Decomposition

TL;DR

This paper introduces the novel task of Blind Image Decomposition, aiming to separate superimposed images into their original components without prior knowledge of the mixing process, and provides benchmarks and a baseline network.

Contribution

It defines the new task of Blind Image Decomposition, creates benchmark datasets, and proposes a baseline neural network model for future research.

Findings

Benchmarks demonstrate the task's feasibility.

The BIDeN network effectively decomposes superimposed images.

Results validate the usefulness of the proposed datasets and model.

Abstract

We propose and study a novel task named Blind Image Decomposition (BID), which requires separating a superimposed image into constituent underlying images in a blind setting, that is, both the source components involved in mixing as well as the mixing mechanism are unknown. For example, rain may consist of multiple components, such as rain streaks, raindrops, snow, and haze. Rainy images can be treated as an arbitrary combination of these components, some of them or all of them. How to decompose superimposed images, like rainy images, into distinct source components is a crucial step toward real-world vision systems. To facilitate research on this new task, we construct multiple benchmark datasets, including mixed image decomposition across multiple domains, real-scenario deraining, and joint shadow/reflection/watermark removal. Moreover, we propose a simple yet general Blind Image Decomposition Network (BIDeN) to serve as a strong baseline for future work. Experimental results demonstrate the tenability of our benchmarks and the effectiveness of BIDeN.