An Effective Image Restorer: Denoising and Luminance Adjustment for Low-photon-count Imaging

TL;DR

This paper introduces a lightweight image restoration framework for low-photon-count imaging that effectively denoises and enhances luminance, improving image quality in photon-scarce conditions.

Contribution

The paper proposes a novel multi-level pyramid denoising network with a luminance adjustment module, incorporating multi-skip attention residual blocks for improved feature representation.

Findings

Achieves superior noise suppression and luminance recovery.

Effectively handles various photon levels in low-light images.

Reduces color distortion during luminance enhancement.

Abstract

Imaging under photon-scarce situations introduces challenges to many applications as the captured images are with low signal-to-noise ratio and poor luminance. In this paper, we investigate the raw image restoration under low-photon-count conditions by simulating the imaging of quanta image sensor (QIS). We develop a lightweight framework, which consists of a multi-level pyramid denoising network (MPDNet) and a luminance adjustment (LA) module to achieve separate denoising and luminance enhancement. The main component of our framework is the multi-skip attention residual block (MARB), which integrates multi-scale feature fusion and attention mechanism for better feature representation. Our MPDNet adopts the idea of Laplacian pyramid to learn the small-scale noise map and larger-scale high-frequency details at different levels, and feature extractions are conducted on the multi-scale input images to encode richer contextual information. Our LA module enhances the luminance of the denoised image by estimating its illumination, which can better avoid color distortion. Extensive experimental results have demonstrated that our image restorer can achieve superior performance on the degraded images with various photon levels by suppressing noise and recovering luminance and color effectively.