Image reconstruction from dense binary pixels

TL;DR

This paper introduces MLNet, a fast neural network for reconstructing images from dense binary pixels, significantly outperforming iterative methods in speed while maintaining high quality, advancing HDR imaging technology.

Contribution

The paper proposes MLNet, a novel neural network architecture that efficiently reconstructs images from dense binary pixels, offering a faster alternative to traditional iterative algorithms.

Findings

MLNet achieves state-of-the-art reconstruction quality.

MLNet is two orders of magnitude faster than iterative methods.

The approach effectively models the binary pixel data for HDR imaging.

Abstract

Recently, the dense binary pixel Gigavision camera had been introduced, emulating a digital version of the photographic film. While seems to be a promising solution for HDR imaging, its output is not directly usable and requires an image reconstruction process. In this work, we formulate this problem as the minimization of a convex objective combining a maximum-likelihood term with a sparse synthesis prior. We present MLNet - a novel feed-forward neural network, producing acceptable output quality at a fixed complexity and is two orders of magnitude faster than iterative algorithms. We present state of the art results in the abstract.