Deep Atrous Guided Filter for Image Restoration in Under Display Cameras

TL;DR

This paper introduces Deep Atrous Guided Filter (DAGF), an end-to-end image restoration method for Under Display Cameras that effectively handles severe image degradation using a two-stage process with multi-scale atrous convolutions.

Contribution

The paper proposes a novel two-stage deep learning framework with atrous convolutions for high-resolution image restoration in UDC systems, including a pre-training scheme to enhance performance.

Findings

Achieved top rankings in RLQ-TOD'20 UDC Challenge for POLED and TOLED displays.

Significant performance improvements over existing methods.

Effective handling of megapixel images through direct training.

Abstract

Under Display Cameras present a promising opportunity for phone manufacturers to achieve bezel-free displays by positioning the camera behind semi-transparent OLED screens. Unfortunately, such imaging systems suffer from severe image degradation due to light attenuation and diffraction effects. In this work, we present Deep Atrous Guided Filter (DAGF), a two-stage, end-to-end approach for image restoration in UDC systems. A Low-Resolution Network first restores image quality at low-resolution, which is subsequently used by the Guided Filter Network as a filtering input to produce a high-resolution output. Besides the initial downsampling, our low-resolution network uses multiple, parallel atrous convolutions to preserve spatial resolution and emulates multi-scale processing. Our approach's ability to directly train on megapixel images results in significant performance improvement. We additionally propose a simple simulation scheme to pre-train our model and boost performance. Our overall framework ranks 2nd and 5th in the RLQ-TOD'20 UDC Challenge for POLED and TOLED displays, respectively.