Gen3DEval: Using vLLMs for Automatic Evaluation of Generated 3D Objects

Rapid advancements in text-to-3D generation require robust and scalable evaluation metrics that align closely with human judgment, a need unmet by current metrics such as PSNR and CLIP, which require ground-truth data or focus only on prompt fidelity. To address this, we introduce Gen3DEval, a novel evaluation framework that leverages vision large language models (vLLMs) specifically fine-tuned for 3D object quality assessment. Gen3DEval evaluates text fidelity, appearance, and surface quality by analyzing 3D surface normals, without requiring ground-truth comparisons, bridging the gap between automated metrics and user preferences. Compared to state-of-the-art task-agnostic models, Gen3DEval demonstrates superior performance in user-aligned evaluations, placing it as a comprehensive and accessible benchmark for future research on text-to-3D generation. The project page can be found here: \href{this https URL}{this https URL}.

@article{maiti2025_2504.08125,
  title={ Gen3DEval: Using vLLMs for Automatic Evaluation of Generated 3D Objects },
  author={ Shalini Maiti and Lourdes Agapito and Filippos Kokkinos },
  journal={arXiv preprint arXiv:2504.08125},
  year={ 2025 }
}