Towards Unified Evaluation of Prompt Enhancers for Video Generation

arXiv:2610.11736 · cs.CV · Submitted 2026-10-08 · Read on arXiv

cs.CV

Submitted: 2026-10-08

Updated: 2026-10-08

Code: https://github.com/yawen-shao/PEBench

Terminology

• Fidelity — 34× in this paper · explained in 2 episodes
• Consistency — 25× in this paper · explained in 3 episodes
• Benchmark — 24× in this paper · explained in 2 episodes
• Directorial Creation — 22× in this paper
• Alignment — 19× in this paper · explained in 1 episode
• Semantic Fidelity — 19× in this paper
• Internal Consistency — 15× in this paper
• Verification — 13× in this paper · explained in 2 episodes
• Core — 6× in this paper · explained in 2 episodes
• Grounding — 6× in this paper · explained in 3 episodes
• Audio Requirement Preservation — 3× in this paper
• Camera Constraint Preservation — 3× in this paper
• Camera Design Specificity — 3× in this paper
• Core-Intent Focus — 3× in this paper
• Evaluation Dimensions — 3× in this paper · explained in 3 episodes
• On-Screen Text Integrity — 3× in this paper
• Physical Logic — 3× in this paper
• Sound Design Integration — 3× in this paper
• Visual Style Specification — 3× in this paper
• Action and Narrative Logic — 2× in this paper
• Computer Vision and Pattern Recognition — 2× in this paper
• Dialogue and Lyrics Integrity — 2× in this paper
• Editing and Transition Design — 2× in this paper
• Generative Model — 2× in this paper · explained in 2 episodes
• Generative Models — 2× in this paper · explained in 2 episodes
• Genre and Style Fidelity — 2× in this paper
• Interpretability — 2× in this paper · explained in 15 episodes
• Lighting and Color Fidelity — 2× in this paper
• Lighting and Color Specification — 2× in this paper
• Scene and Spatial Preservation — 2× in this paper
• Subject and Attribute Continuity — 2× in this paper
• Subject and Attribute Preservation — 2× in this paper
• Temporal and State Continuity — 2× in this paper
• Action and Narrative Fidelity — 1× in this paper
• Adam — 1× in this paper · explained in 2 episodes
• Benchmarking — 1× in this paper · explained in 3 episodes
• Bradley-Terry model — 1× in this paper · explained in 2 episodes
• Calibration — 1× in this paper · explained in 7 episodes
• Diffusion Model — 1× in this paper · explained in 8 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• Hallucination — 1× in this paper · explained in 3 episodes
• Iterative Refinement — 1× in this paper · explained in 3 episodes
• Multimodal Dataset — 1× in this paper · explained in 2 episodes
• Narrative Development and Engagement — 1× in this paper
• Redundancy — 1× in this paper · explained in 2 episodes
• Semantic Alignment — 1× in this paper · explained in 3 episodes
• Storyboard and Timing Completeness — 1× in this paper
• Subject and Performance Specificity — 1× in this paper
• Test-time Scaling — 1× in this paper · explained in 2 episodes

Sources

• WanPE: Towards Cinematic Prompt Enhancement for Modern Text-to-Video Generation
• VPO: Aligning Text-to-Video Generation Models with Prompt Optimization
• SCMAPR: Self-Correcting Multi-Agent Prompt Refinement for Complex-Scenario Text-to-Video Generation
• Prompt-A-Video: Prompt Your Video Diffusion Model via Preference-Aligned LLM
• RAPO++: Cross-Stage Prompt Optimization for Text-to-Video Generation via Data Alignment and Test-Time Scaling
• CAPE-T2V: Captioner-Anchored Prompt Enhancement toward Two-Sided Conditioning Alignment in Text-to-Video Generation
• VISTA: A Test-Time Self-Improving Video Generation Agent
• Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence
• Gemma 4 Technical Report
• VBench: Comprehensive Benchmark Suite for Video Generative Models
• OpenS2V-Nexus: A Detailed Benchmark and Million-Scale Dataset for Subject-to-Video Generation
• UniVBench: Towards Unified Evaluation for Video Foundation Models
• MSAVBench: Towards Comprehensive and Reliable Evaluation of Multi-Shot Audio-Video Generation
• OpenSubject: Leveraging Video-Derived Identity and Diversity Priors for Subject-driven Image Generation and Manipulation
• Goku: A Million-Scale Universal Dataset and Benchmark for Instruction-Based Video Editing
• Wan-Image: Pushing the Boundaries of Generative Visual Intelligence
• Seedream 4.0: Toward Next-generation Multimodal Image Generation
• Qwen3.5-Omni Technical Report

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models