Challenging Cases of Neural Image Compression: A Dataset of Visually Compelling Yet Semantically Incorrect Reconstructions

摘要

Preserving the semantic integrity of image details is difficult in neural image compression. Failure to do so can result in miscompressions: reconstruction errors that change the meaning between the original and reconstructed images. Undetected miscompressions can compromise the reliability of reconstructed images and potentially reduce the accuracy of downstream computer vision tasks. To advance research on this problem, we present SCLIC, a curated dataset of 18k human-annotated miscompressions generated by 12 neural compression models. It includes images from three common benchmark datasets, compressed and reconstructed using codecs based on CNNs, GANs, diffusion models, and image transformers for different perceptual metrics and rate-distortion settings. We envision that this dataset will facilitate the development of strategies to mitigate miscompressions and enable more reliable neural image compression codecs.