Reconstruction of Videos Taken by a Non-Regular Sampling Sensor

TL;DR

This paper introduces a multi-frame reconstruction method for videos captured by non-regular sampling sensors, leveraging temporal correlations to improve image quality over single-frame approaches.

Contribution

It proposes a novel multi-frame reconstruction technique that enhances video quality by exploiting temporal correlations in non-regular sampling sensor data.

Findings

Achieves up to 1.19 dB higher PSNR compared to single-frame methods.

Utilizes temporal correlation to improve reconstruction quality.

Demonstrates visually noticeable improvements in reconstructed videos.

Abstract

Recently, it has been shown that a high resolution image can be obtained without the usage of a high resolution sensor. The main idea has been that a low resolution sensor is covered with a non-regular sampling mask followed by a reconstruction of the incomplete high resolution image captured this way. In this paper, a multi-frame reconstruction approach is proposed where a video is taken by a non-regular sampling sensor and fully reconstructed afterwards. By utilizing the temporal correlation between neighboring frames, the reconstruction quality can be further enhanced. Compared to a state-of-the-art single-frame reconstruction approach, this leads to a visually noticeable gain in PSNR of up to 1.19 dB on average.