PyTorch Image Quality: Metrics for Image Quality Assessment
This provides a usability-centric tool for researchers and practitioners in computer vision and image processing, though it is incremental as it focuses on implementation rather than new algorithms.
The authors tackled the need for reliable and efficient Image Quality Assessment (IQA) metrics by presenting PyTorch Image Quality (PIQ), a library that implements popular IQA algorithms with verified correctness and GPU acceleration, resulting in benchmarks showcasing performance-time trade-offs.
Image Quality Assessment (IQA) metrics are widely used to quantitatively estimate the extent of image degradation following some forming, restoring, transforming, or enhancing algorithms. We present PyTorch Image Quality (PIQ), a usability-centric library that contains the most popular modern IQA algorithms, guaranteed to be correctly implemented according to their original propositions and thoroughly verified. In this paper, we detail the principles behind the foundation of the library, describe the evaluation strategy that makes it reliable, provide the benchmarks that showcase the performance-time trade-offs, and underline the benefits of GPU acceleration given the library is used within the PyTorch backend. PyTorch Image Quality is an open source software: https://github.com/photosynthesis-team/piq/.