Image reconstruction from dense binary pixels
This work addresses image reconstruction for HDR imaging using a novel camera technology, offering a significant speed improvement for practical applications.
The paper tackles the problem of reconstructing images from dense binary pixels produced by a Gigavision camera, which is not directly usable for HDR imaging, by introducing MLNet, a feed-forward neural network that achieves acceptable output quality with fixed complexity and is two orders of magnitude faster than iterative algorithms.
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.