Computational Image Formation: Simulators in the Deep Learning Era

TL;DR

This paper introduces the concept of computational image formation (CIF), emphasizing the design of simulators that mimic physical degradation processes to enhance image reconstruction in challenging conditions.

Contribution

It conceptualizes CIF, discusses its key attributes, and provides case studies and examples demonstrating its application in various imaging scenarios.

Findings

CIF simulators need to be accurate, fast, well-posed, and differentiable.

Multiple existing simulators are evaluated for imaging through atmospheric turbulence.

CIF can be applied to diverse problems like bad weather imaging and dynamic vision sensors.

Abstract

At the pinnacle of computational imaging is the co-optimization of camera and algorithm. This, however, is not the only form of computational imaging. In problems such as imaging through adverse weather, the bigger challenge is how to accurately simulate the forward degradation process so that we can synthesize data to train reconstruction models and/or integrating the forward model as part of the reconstruction algorithm. This article introduces the concept of computational image formation (CIF). Compared to the standard inverse problems where the goal is to recover the latent image $x$ from the observation $y = G(x)$, CIF shifts the focus to designing an approximate mapping $H$ such that $H \approx G$ while giving a good image reconstruction result. The word "computational" highlights the fact that the image formation is now replaced by a numerical simulator. While matching the mother nature remains an important goal, CIF pays even greater attention on strategically choosing an $H$ so that the reconstruction performance is maximized. The goal of this article is to conceptualize the idea of CIF by elaborating on its meaning and implications. The first part of the article is a discussion on the four attributes of a CIF simulator: accurate enough to mimic $G$, fast enough to be integrated as part of the reconstruction, provides a well-posed inverse problem when plugged into the reconstruction, and differentiable to allow backpropagation. The second part of the article is a detailed case study based on imaging through atmospheric turbulence. A plethora of simulators, old and new ones, are discussed. The third part of the article is a collection of other examples that fall into the category of CIF, including imaging through bad weather, dynamic vision sensors, and differentiable optics. Finally, thoughts about the future direction and recommendations to the community are shared.