Saved in:
Bibliographic Details
Main Authors: Rahman, Zillur, Sheng, Alex, Meo, Cristian
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.01509
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914363079655424
author Rahman, Zillur
Sheng, Alex
Meo, Cristian
author_facet Rahman, Zillur
Sheng, Alex
Meo, Cristian
contents While large-scale datasets have driven significant progress in Text-to-Video (T2V) generative models, these models remain highly sensitive to input prompts, demonstrating that prompt design is critical to generation quality. Current methods for improving video output often fall short: they either depend on complex, post-editing models, risking the introduction of artifacts, or require expensive fine-tuning of the core generator, which severely limits both scalability and accessibility. In this work, we introduce 3R, a novel RAG based prompt optimization framework. 3R utilizes the power of current state-of-the-art T2V diffusion model and vision language model. It can be used with any T2V model without any kind of model training. The framework leverages three key strategies: RAG-based modifiers extraction for enriched contextual grounding, diffusion-based Preference Optimization for aligning outputs with human preferences, and temporal frame interpolation for producing temporally consistent visual contents. Together, these components enable more accurate, efficient, and contextually aligned text-to-video generation. Experimental results demonstrate the efficacy of 3R in enhancing the static fidelity and dynamic coherence of generated videos, underscoring the importance of optimizing user prompts.
format Preprint
id arxiv_https___arxiv_org_abs_2603_01509
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Retrieval, Refinement, and Ranking for Text-to-Video Generation via Prompt Optimization and Test-Time Scaling
Rahman, Zillur
Sheng, Alex
Meo, Cristian
Computer Vision and Pattern Recognition
Artificial Intelligence
While large-scale datasets have driven significant progress in Text-to-Video (T2V) generative models, these models remain highly sensitive to input prompts, demonstrating that prompt design is critical to generation quality. Current methods for improving video output often fall short: they either depend on complex, post-editing models, risking the introduction of artifacts, or require expensive fine-tuning of the core generator, which severely limits both scalability and accessibility. In this work, we introduce 3R, a novel RAG based prompt optimization framework. 3R utilizes the power of current state-of-the-art T2V diffusion model and vision language model. It can be used with any T2V model without any kind of model training. The framework leverages three key strategies: RAG-based modifiers extraction for enriched contextual grounding, diffusion-based Preference Optimization for aligning outputs with human preferences, and temporal frame interpolation for producing temporally consistent visual contents. Together, these components enable more accurate, efficient, and contextually aligned text-to-video generation. Experimental results demonstrate the efficacy of 3R in enhancing the static fidelity and dynamic coherence of generated videos, underscoring the importance of optimizing user prompts.
title Retrieval, Refinement, and Ranking for Text-to-Video Generation via Prompt Optimization and Test-Time Scaling
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2603.01509