DreamBench++：一個針對個性化圖像生成的與人類對齊的基準。

DreamBench++: A Human-Aligned Benchmark for Personalized Image Generation

June 24, 2024

作者: Yuang Peng, Yuxin Cui, Haomiao Tang, Zekun Qi, Runpei Dong, Jing Bai, Chunrui Han, Zheng Ge, Xiangyu Zhang, Shu-Tao Xia

cs.AI

摘要

個性化圖像生成在協助人們日常工作和生活方面具有巨大潛力，因為它在創造性生成個性化內容方面具有出色的功能。然而，目前的評估要麼是自動化的，但與人類不一致，要麼需要耗時且昂貴的人工評估。在這項工作中，我們提出了DreamBench++，這是一個由先進的多模態GPT模型自動化的與人類一致的基準。具體來說，我們系統地設計提示，讓GPT既與人類一致又自我一致，並賦予任務強化的能力。此外，我們構建了一個包含多樣圖像和提示的全面數據集。通過對7種現代生成模型進行基準測試，我們展示了DreamBench++在顯著提高與人類一致的評估方面的成果，有助於推動社區獲得創新性發現。

English

Personalized image generation holds great promise in assisting humans in everyday work and life due to its impressive function in creatively generating personalized content. However, current evaluations either are automated but misalign with humans or require human evaluations that are time-consuming and expensive. In this work, we present DreamBench++, a human-aligned benchmark automated by advanced multimodal GPT models. Specifically, we systematically design the prompts to let GPT be both human-aligned and self-aligned, empowered with task reinforcement. Further, we construct a comprehensive dataset comprising diverse images and prompts. By benchmarking 7 modern generative models, we demonstrate that DreamBench++ results in significantly more human-aligned evaluation, helping boost the community with innovative findings.