UDC-VIT: A Real-World Video Dataset for Under-Display Cameras

TL;DR

This paper introduces UDC-VIT, a real-world video dataset capturing under-display camera degradation effects, and demonstrates its importance for training effective face recognition models.

Contribution

The creation of UDC-VIT, the first real-world UDC video dataset focusing on human facial recognition, and the analysis showing the limitations of synthetic datasets.

Findings

Models trained on synthetic datasets perform poorly on real UDC videos.

Effective UDC restoration improves face recognition accuracy.

Frame-by-frame alignment using DFT enhances dataset quality.

Abstract

Even though an Under-Display Camera (UDC) is an advanced imaging system, the display panel significantly degrades captured images or videos, introducing low transmittance, blur, noise, and flare issues. Tackling such issues is challenging because of the complex degradation of UDCs, including diverse flare patterns. However, no dataset contains videos of real-world UDC degradation. In this paper, we propose a real-world UDC video dataset called UDC-VIT. Unlike existing datasets, UDC-VIT exclusively includes human motions for facial recognition. We propose a video-capturing system to acquire clean and UDC-degraded videos of the same scene simultaneously. Then, we align a pair of captured videos frame by frame, using discrete Fourier transform (DFT). We compare UDC-VIT with six representative UDC still image datasets and two existing UDC video datasets. Using six deep-learning models, we compare UDC-VIT and an existing synthetic UDC video dataset. The results indicate the ineffectiveness of models trained on earlier synthetic UDC video datasets, as they do not reflect the actual characteristics of UDC-degraded videos. We also demonstrate the importance of effective UDC restoration by evaluating face recognition accuracy concerning PSNR, SSIM, and LPIPS scores. UDC-VIT is available at our official GitHub repository.