Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Exposure Correction Model to Enhance Image Quality

About

Exposure errors in an image cause a degradation in the contrast and low visibility in the content. In this paper, we address this problem and propose an end-to-end exposure correction model in order to handle both under- and overexposure errors with a single model. Our model contains an image encoder, consecutive residual blocks, and image decoder to synthesize the corrected image. We utilize perceptual loss, feature matching loss, and multi-scale discriminator to increase the quality of the generated image as well as to make the training more stable. The experimental results indicate the effectiveness of proposed model. We achieve the state-of-the-art result on a large-scale exposure dataset. Besides, we investigate the effect of exposure setting of the image on the portrait matting task. We find that under- and overexposed images cause severe degradation in the performance of the portrait matting models. We show that after applying exposure correction with the proposed model, the portrait matting quality increases significantly. https://github.com/yamand16/ExposureCorrection

Fevziye Irem Eyiokur, Dogucan Yaman, Haz{\i}m Kemal Ekenel, Alexander Waibel• 2022

Related benchmarks

TaskDatasetResultRank
Multiple Exposure CorrectionMSEC Under 1 (test)
PSNR20.71
35
Multiple Exposure CorrectionMSEC Over 1 (test)
PSNR20.99
35
Exposure CorrectionMSEC Average 1 (test)
PSNR20.87
21
Exposure CorrectionLOL dataset (test)
PSNR15.3733
5
Exposure CorrectionNVIDIA RTX 3090
Speed (FPS)34
4
Showing 5 of 5 rows

Other info

Follow for update