Exposure Correction Model to Enhance Image Quality

Eyiokur, Fevziye Irem; Yaman, Dogucan; Ekenel, Hazım Kemal; Waibel, Alexander

doi:10.1109/cvprw56347.2022.00083

Cited by 8 publications

(3 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…4 shows an example of the task of exposure adjustment. We selected the GAN-based exposure correction approach of [9] for this experiment. We used the pre-trained model released by the authors 1 .…”

Section: A Black-box Neural Isp Modulementioning

confidence: 99%

See 1 more Smart Citation

Advocating Pixel-Level Authentication of Camera-Captured Images

Punnappurath,

Zhao,

Abdelhamed

et al. 2024

IEEE Access

View full text Add to dashboard Cite

The authenticity of digital images posted online and shared on social media is often questioned due to the ability of photo-editing software to alter image content and generative AI methods that can produce visually compelling deepfakes. Only images directly produced by cameras are deemed unaltered and beyond suspicion, as they have not undergone any modifications. However, there is a recent trend among camera manufacturers to integrate AI-based modules into the dedicated onboard hardware, specifically the image signal processor (ISP), responsible for processing the captured sensor image into the final saved image for users. Many of these AI modules utilize perceptual or generative losses during training, which can ''hallucinate'' image content. While this hallucinated content often manifests as small details and textures, there are instances where these regions unintentionally impact the interpretation of the entire image. This paper aims to bring attention to this issue and advocate for in-camera strategies to validate the authenticity of camera-captured images at a pixel level. We propose the creation of an "authenticity" mask that could be stored as additional metadata with each image. This information can be extracted and overlaid on the image to easily identify the hallucinated regions. Considering the widespread implications of image authenticity (e.g., in courtroom evidence, news broadcasts, and other media forms), we anticipate that authentication metadata will become a standard practice for any ISP utilizing AI.

show abstract

Section: A Black-box Neural Isp Modulementioning

confidence: 99%

“…The image has a lot of saturated pixels, particularly in the sky region. The second column shows the output of [9]. Using a GAN loss for this module results in cloud-like details being hallucinated where there were originally only saturated pixels (i.e., no information).…”

Section: A Black-box Neural Isp Modulementioning

confidence: 99%

Advocating Pixel-Level Authentication of Camera-Captured Images

Punnappurath,

Zhao,

Abdelhamed

et al. 2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…In addition, multi-exposure fusion methods [30,31,33,34,38] are powerless when there is only one image of the same scene. These limitation have spurred the development of new approaches [1,7,11,45,52] for tackling multiple exposure errors.…”

Section: Introductionmentioning

confidence: 99%