Loading [a11y]/accessibility-menu.js
4K-Resolution Photo Exposure Correction at 125 FPS with ~8K Parameters | IEEE Conference Publication | IEEE Xplore

4K-Resolution Photo Exposure Correction at 125 FPS with ~8K Parameters


Abstract:

The illumination of improperly exposed photographs has been widely corrected using deep convolutional neural networks or Transformers. Despite with promising performance,...Show More

Abstract:

The illumination of improperly exposed photographs has been widely corrected using deep convolutional neural networks or Transformers. Despite with promising performance, these methods usually suffer from large parameter amounts and heavy computational FLOPs on high-resolution photographs. In this paper, we propose extremely light-weight (with only ~8K parameters) Multi-Scale Linear Transformation (MSLT) networks under the multi-layer perception architecture, which can process 4K-resolution sRGB images at 125 Frame-Per-Second (FPS) by a Titan RTX GPU. Specifically, the proposed MSLT networks first decompose an input image into high and low frequency layers by Laplacian pyramid techniques, and then sequentially correct different layers by pixel-adaptive linear transformation, which is implemented by efficient bilateral grid learning or 1 × 1 convolutions. Experiments on two benchmark datasets demonstrate the efficiency of our MSLTs against the state-of-the-arts on photo exposure correction. Extensive ablation studies validate the effectiveness of our contributions. The code is available at https://github.com/Zhou-Yijie/MSLTNet.
Date of Conference: 03-08 January 2024
Date Added to IEEE Xplore: 09 April 2024
ISBN Information:

ISSN Information:

Conference Location: Waikoloa, HI, USA

Funding Agency:


1. Introduction

The prevalence of smartphones with cameras encourages people to take snapshots of their daily life like photographers. However, inaccurate setting of shutter speed, focal-aperture ratio and/or ISO value may bring improper exposure to the captured photographs with degradation on visual quality [4]. To adjust the photo exposure properly for visually appealing purpose, it is essential to develop efficient exposure correction methods for edge devices.

References

References is not available for this document.