Artifact Detection Maps Learned using Shallow Convolutional Networks

Automatically identifying the locations and severities of video artifacts is a difficult problem. We have developed a general method for detecting local artifacts by learning differences between distorted and pristine video frames. Our model, which we call the Video Impairment Mapper (VID-MAP), produces a full resolution map of artifact detection probabilities based on comparisons of exitatory and inhibatory convolutional responses. Validation on a large database shows that our method outperforms the previous state-of-the-art. A software release of VID-MAP that was trained to produce upscaling and combing detection probability maps is available online: http://live.ece.utexas.edu/research/quality/VIDMAP release.zip for public use and evaluation.