SynArtifact: Classifying and Alleviating Artifacts in Synthetic Images via Vision-Language Model

arXiv:2402.18068v1 Announce Type: new
Abstract: In the rapidly evolving area of image synthesis, a serious challenge is the presence of complex artifacts that compromise perceptual realism of synthetic images. To alleviate artifacts and improve quality of synthetic images, we fine-tune Vision-Language Model (VLM) as artifact classifier to automatically identify and classify a wide range of artifacts and provide supervision for further optimizing generative models. Specifically, we develop a comprehensive artifact taxonomy and construct a dataset of synthetic images with artifact …

abstract artifact arxiv challenge classifier cs.cv identify image images language language model quality synthesis synthetic type via vision vlm