On Aliased Resizing and Surprising Subtleties in GAN Evaluation

Understand

Metrics for evaluating generative models aim to measure the discrepancy between real and generated images.

• The often-used Frechet Inception Distance (FID) metric, for example, extracts "high-level" features using a deep network from the two sets.
• However, we find that the differences in "low-level" preprocessing, specifically image resizing and compression, can induce large variations and have unforeseen consequences.
• For instance, when resizing an image, e.g., with a bilinear or bicubic kernel, signal processing principles mandate adjusting prefilter width depending on the downsampling factor, to antialias to the appropriate bandwidth.