AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

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

Cihang Peng, Qiming Hou, Zhong Ren, Kun Zhou

ICCV 2025 · Vision-language and multimodal › Multimodal LLMs · approach: Interleaved image-text generation with MLLMs · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
pre-detection VLM-LLM re-captioning instead of web caption to OVD (ablation)ROVI pipeline · Data generation methods (5K images)distinct categories: 3001 -> 25374Improved
pre-detection VLM-LLM re-captioning instead of VLM description sent directly to OVD (ablation)ROVI pipeline · Data generation methods (5K images)avg boxes per image: 9.20 -> 24.01Improved
pre-detection VLM-LLM re-captioning instead of RAM tagging then OVD (ablation)ROVI pipeline · Data generation methods (5K images)avg boxes per image: 11.54 -> 24.01Improved
replace RAM with RAM++ tagging (ablation)InstanceDiffusion-style pipeline · Data generation methods (5K images)avg boxes per image: 11.54 -> 11.58No clear effect
fuse four OVDs instead of a single detector (ablation)ROVI detection stage · 5K sampled imagesunique category share: 17.0%, 11.9%, 15.8%, 9.4% unique categories per OVDImproved
train GLIGEN on ROVI instead of official dataGLIGEN (SD v1.4) · ROVI validation setFID: 19.3 -> 15.7Improved
train GLIGEN on ROVI instead of official dataGLIGEN (SD v1.4) · ROVI validation setaesthetic score: 5.33 -> 5.83Improved
train GLIGEN on ROVI instead of official dataGLIGEN (SD v1.4) · ROVI validation setinstance pass rate: 0.750 -> 0.880Improved
train GLIGEN on ROVI instead of official dataGLIGEN (SD v1.4) · Open Images validation setinstance pass rate: 0.812 -> 0.872Improved
fine-tune with instance grounding on ROVI vs base SD v1.4GLIGEN (SD v1.4) · ROVI validation setCLIP similarity: 0.283 -> 0.286No clear effect
GLIGEN on ROVI vs InstanceDiffusion in user studyGLIGEN (SD v1.4) · User study (200 inputs)aesthetic win rate: 83.3%Improved
GLIGEN on ROVI vs MIGC in user studyGLIGEN (SD v1.4) · User study (200 inputs)instance alignment win rate: 94.8%Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy