Perceptual AI-based Metrics

Detail Preservation Evaluation on realistic scene

DXOMARK developed machine learning-based methods that estimate the perceptual image quality perceived by a human expert when evaluating pictures of known content. The detail preservation metric quantifies the capacity of a camera to produce sharp images precisely and pleasantly based on a trained dataset of the scene. 

Read more →

Key Highlights

  • Photo & Video measurements
  • Detail Preservation Metric
  • Perceptual Noise Quality Metric

Related Links and Documents