Papers
arxiv:2508.01008

ROVI: A VLM-LLM Re-Captioned Dataset for Open-Vocabulary Instance-Grounded Text-to-Image Generation

Published on Aug 1
Authors:
,
,

Abstract

ROVI, a synthetic dataset for text-to-image generation, uses re-captioning to enhance instance-grounded detection and improves image quality, resolution, and category diversity over existing datasets.

AI-generated summary

We present ROVI, a high-quality synthetic dataset for instance-grounded text-to-image generation, created by labeling 1M curated web images. Our key innovation is a strategy called re-captioning, focusing on the pre-detection stage, where a VLM (Vision-Language Model) generates comprehensive visual descriptions that are then processed by an LLM (Large Language Model) to extract a flat list of potential categories for OVDs (Open-Vocabulary Detectors) to detect. This approach yields a global prompt inherently linked to instance annotations while capturing secondary visual elements humans typically overlook. Evaluations show that ROVI exceeds existing detection datasets in image quality and resolution while containing two orders of magnitude more categories with an open-vocabulary nature. For demonstrative purposes, a text-to-image model GLIGEN trained on ROVI significantly outperforms state-of-the-art alternatives in instance grounding accuracy, prompt fidelity, and aesthetic quality. Our dataset and reproducible pipeline are available at https://github.com/CihangPeng/ROVI.

Community

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2508.01008 in a model README.md to link it from this page.

Datasets citing this paper 1

Spaces citing this paper 1

Collections including this paper 1