Cartoon Hallucinations Detection: Pose-aware In Context Visual Learning

arXiv:2403.15048v1 Announce Type: cross
Abstract: Large-scale Text-to-Image (TTI) models have become a common approach for generating training data in various generative fields. However, visual hallucinations, which contain perceptually critical defects, remain a concern, especially in non-photorealistic styles like cartoon characters. We propose a novel visual hallucination detection system for cartoon character images generated by TTI models. Our approach leverages pose-aware in-context visual learning (PA-ICVL) with Vision-Language Models (VLMs), utilizing both RGB images and pose information. By incorporating pose guidance from …

abstract arxiv become cartoon characters context cs.ai cs.cv cs.lg cs.mm data defects detection fields generative hallucination hallucinations however image images novel photorealistic scale text text-to-image training training data type visual