GPT-4V(ision) 是文本到3D生成的人类对齐评估器
GPT-4V(ision) is a Human-Aligned Evaluator for Text-to-3D Generation
AI总结:
本文提出一种基于GPT-4V的自动、多功能且与人类对齐的文本到3D生成评估指标,通过生成评估提示、指导模型成对比较3D资产并计算Elo评级,实验证明其与人类偏好高度一致。
摘要:
尽管文本到3D生成方法近期取得了进展,但仍明显缺乏可靠的评估指标。现有指标通常各自关注单一标准,例如资产与输入文本的对齐程度。这些指标缺乏泛化到不同评估标准的灵活性,且可能无法与人类偏好良好对齐。进行用户偏好研究是一种替代方案,能提供适应性和与人类对齐的结果,但用户研究在规模扩展上成本极高。本文提出了一种用于文本到3D生成模型的自动、多功能且与人类对齐的评估指标。为此,我们首先使用GPT-4V开发了一个提示生成器来生成评估提示,作为比较文本到3D模型的输入。我们进一步设计了一种方法,指导GPT-4V根据用户定义的标准比较两个3D资产。最后,我们使用这些成对比较结果为这些模型分配Elo评级。实验结果表明,我们的指标在不同评估标准下均与人类偏好高度对齐。
英文摘要:
Despite recent advances in text-to-3D generative methods, there is a notable absence of reliable evaluation metrics. Existing metrics usually focus on a single criterion each, such as how well the asset aligned with the input text. These metrics lack the flexibility to generalize to different evaluation criteria and might not align well with human preferences. Conducting user preference studies is an alternative that offers both adaptability and human-aligned results. User studies, however, can be very expensive to scale. This paper presents an automatic, versatile, and human-aligned evaluation metric for text-to-3D generative models. To this end, we first develop a prompt generator using GPT-4V to generate evaluating prompts, which serve as input to compare text-to-3D models. We further design a method instructing GPT-4V to compare two 3D assets according to user-defined criteria. Finally, we use these pairwise comparison results to assign these models Elo ratings. Experimental results suggest our metric strongly align with human preference across different evaluation criteria.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。