Visual Personalization Turing Test
This addresses the problem of evaluating personalized generative AI for researchers and developers by shifting focus from identity replication to perceptual plausibility, offering a scalable and privacy-safe approach.
The paper introduces the Visual Personalization Turing Test (VPTT), a new paradigm for evaluating contextual visual personalization by assessing perceptual indistinguishability from plausible user-generated content, and presents a framework including a benchmark and a retrieval-augmented generator that achieves high correlation with human and VLM judgments.
We introduce the Visual Personalization Turing Test (VPTT), a new paradigm for evaluating contextual visual personalization based on perceptual indistinguishability, rather than identity replication. A model passes the VPTT if its output (image, video, 3D asset, etc.) is indistinguishable to a human or calibrated VLM judge from content a given person might plausibly create or share. To operationalize VPTT, we present the VPTT Framework, integrating a 10k-persona benchmark (VPTT-Bench), a visual retrieval-augmented generator (VPRAG), and the VPTT Score, a text-only metric calibrated against human and VLM judgments. We show high correlation across human, VLM, and VPTT evaluations, validating the VPTT Score as a reliable perceptual proxy. Experiments demonstrate that VPRAG achieves the best alignment-originality balance, offering a scalable and privacy-safe foundation for personalized generative AI.