UDC 2020 Challenge on Image Restoration of Under-Display Camera: Methods and Results

TL;DR

This paper reports on the first challenge for image restoration of Under-Display Cameras, presenting new datasets, methods from multiple teams, and state-of-the-art results for two display types, advancing the field significantly.

Contribution

It introduces a new dataset and benchmark for UDC image restoration, and provides a comprehensive comparison of methods from 150 teams, establishing state-of-the-art performance.

Findings

State-of-the-art restoration performance achieved

Effective methods identified for T-OLED and P-OLED displays

Benchmark datasets released for future research

Abstract

This paper is the report of the first Under-Display Camera (UDC) image restoration challenge in conjunction with the RLQ workshop at ECCV 2020. The challenge is based on a newly-collected database of Under-Display Camera. The challenge tracks correspond to two types of display: a 4k Transparent OLED (T-OLED) and a phone Pentile OLED (P-OLED). Along with about 150 teams registered the challenge, eight and nine teams submitted the results during the testing phase for each track. The results in the paper are state-of-the-art restoration performance of Under-Display Camera Restoration. Datasets and paper are available at https://yzhouas.github.io/projects/UDC/udc.html.