# MSVBench: Towards Human-Level Evaluation of Multi-Shot Video Generation

arXiv: https://arxiv.org/abs/2602.23969 · HTML: https://mlsanity.com/paper/2602.23969/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 41 references that are in the map.
- First posted on arXiv 27 Feb 2026.

## Builds on (most cited first, 29 of 29)

- [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025)
- [RAFT: Recurrent All-Pairs Field Transforms for Optical Flow](https://mlsanity.com/paper/2003.12039/) (2020)
- [CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer](https://mlsanity.com/paper/2408.06072/) (2024)
- [VBench: Comprehensive Benchmark Suite for Video Generative Models](https://mlsanity.com/paper/2311.17982/) (2023)
- [MUSIQ: Multi-scale Image Quality Transformer](https://mlsanity.com/paper/2108.05997/) (2021)
- [Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion](https://mlsanity.com/paper/2506.08009/) (2025)
- [LTX-Video: Realtime Video Latent Diffusion](https://mlsanity.com/paper/2501.00103/) (2024)
- [VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking](https://mlsanity.com/paper/2303.16727/) (2023)
- [Evaluating Text-to-Visual Generation with Image-to-Text Generation](https://mlsanity.com/paper/2404.01291/) (2024)
- [MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion](https://mlsanity.com/paper/2410.03825/) (2024)
- [EvalCrafter: Benchmarking and Evaluating Large Video Generation Models](https://mlsanity.com/paper/2310.11440/) (2023)
- [Exploring Video Quality Assessment on User Generated Contents from Aesthetic and Technical Perspectives](https://mlsanity.com/paper/2211.04894/) (2022)
- [StoryDiffusion: Consistent Self-Attention for Long-Range Image and Video Generation](https://mlsanity.com/paper/2405.01434/) (2024)
- [Rolling Forcing: Autoregressive Long Video Diffusion in Real Time](https://mlsanity.com/paper/2509.25161/) (2025)
- [Measuring Style Similarity in Diffusion Models](https://mlsanity.com/paper/2404.01292/) (2024)
- [One-Minute Video Generation with Test-Time Training](https://mlsanity.com/paper/2504.05298/) (2025)
- [Perception, Reason, Think, and Plan: A Survey on Large Multimodal Reasoning Models](https://mlsanity.com/paper/2505.04921/) (2025)
- [Automated Movie Generation via Multi-Agent CoT Planning](https://mlsanity.com/paper/2503.07314/) (2025)
- [OpenS2V-Nexus: A Detailed Benchmark and Million-Scale Dataset for Subject-to-Video Generation](https://mlsanity.com/paper/2505.20292/) (2025)
- [MVHumanNet: A Large-scale Dataset of Multi-view Daily Dressing Human Captures](https://mlsanity.com/paper/2312.02963/) (2023)
- [HoloCine: Holistic Generation of Cinematic Multi-Shot Long Video Narratives](https://mlsanity.com/paper/2510.20822/) (2025)
- [Anim-Director: A Large Multimodal Model Powered Agent for Controllable Animation Video Generation](https://mlsanity.com/paper/2408.09787/) (2024)
- [KaLM-Embedding-V2: Superior Training Techniques and Data Inspire A Versatile Embedding Model](https://mlsanity.com/paper/2506.20923/) (2025)
- [FilmAgent: A Multi-Agent Framework for End-to-End Film Automation in Virtual 3D Spaces](https://mlsanity.com/paper/2501.12909/) (2025)
- [FilMaster: Bridging Cinematic Principles and Generative AI for Automated Film Generation](https://mlsanity.com/paper/2506.18899/) (2025)
- [MM-StoryAgent: Immersive Narrated Storybook Video Generation with a Multi-Agent Paradigm across Text, Image and Audio](https://mlsanity.com/paper/2503.05242/) (2025)
- [Uni-MoE-2.0-Omni: Scaling Language-Centric Omnimodal Large Model with Advanced MoE, Training and Data](https://mlsanity.com/paper/2511.12609/) (2025)
- [AniSora: Exploring the Frontiers of Animation Video Generation in the Sora Era](https://mlsanity.com/paper/2412.10255/) (2024)
- [AniWho : A Quick and Accurate Way to Classify Anime Character Faces in Images](https://mlsanity.com/paper/2208.11012/) (2022)

## Built on by (most cited first, 12 of 12)

- [MSAVBench: Towards Comprehensive and Reliable Evaluation of Multi-Shot Audio-Video Generation](https://mlsanity.com/paper/2605.20183/) (2026)
- [LongAV-Compass: Towards Unified Evaluation of Minute-Scale Audio-Visual Generation Across T2AV, I2AV, and V2AV](https://mlsanity.com/paper/2605.26244/) (2026)
- [EntityBench: Towards Entity-Consistent Long-Range Multi-Shot Video Generation](https://mlsanity.com/paper/2605.15199/) (2026)
- [ReCA: Multi-Shot Long Video Extrapolation via Recursive Context Allocation](https://mlsanity.com/paper/2605.26525/) (2026)
- [CineDance: Towards Next-Generation Multi-Shot Long-Form Cinematic Audio-Video Generation](https://mlsanity.com/paper/2606.09639/) (2026)
- [EvalVerse: Pipeline-Aware and Expert-Calibrated Benchmarking for Professional Cinematic Video Generation](https://mlsanity.com/paper/2605.23271/) (2026)
- [KeyFrame-Compass: Towards Comprehensive Evaluation of Keyframe-Conditioned Video Generation](https://mlsanity.com/paper/2607.14202/) (2026)
- [CineForge: Self-Improving Agents for Long-Horizon Video Generation](https://mlsanity.com/paper/2608.29621/) (2026)
- [MAVIN: Multi-Shot Audio-Visual Generation with Customized Narrative Control](https://mlsanity.com/paper/2606.29473/) (2026)
- [KathaTrace: Diagnosing Semantic Trajectory Collapse in Generated Visual Narratives](https://mlsanity.com/paper/2607.01312/) (2026)
- [PersonaShot: Benchmarking Person-Centric Narrative Continuity in Multi-Shot Video Generation](https://mlsanity.com/paper/2608.16717/) (2026)
- [DramaChain Bench: An End-to-End Benchmark for Short-Drama Generation](https://mlsanity.com/paper/2609.00646/) (2026)

## Abstract (arXiv)

The evolution of video generation toward complex, multi-shot narratives has exposed a critical deficit in current evaluation methods. Existing benchmarks remain anchored to single-shot paradigms, lacking the comprehensive story assets and cross-shot metrics required to assess long-form coherence and appeal. To bridge this gap, we introduce MSVBench, the first comprehensive benchmark featuring hierarchical scripts and reference images tailored for Multi-Shot Video generation. We propose a hybrid evaluation framework that synergizes the high-level semantic reasoning of Large Multimodal Models (LMMs) with the fine-grained perceptual rigor of domain-specific expert models. Evaluating 20 video generation methods across diverse paradigms, we find that current models--despite strong visual fidelity--primarily behave as visual interpolators rather than true world models. We further validate the reliability of our benchmark by demonstrating a state-of-the-art Spearman's rank correlation of 94.4% with human judgments. Finally, MSVBench extends beyond evaluation by providing a scalable supervisory signal. Fine-tuning a lightweight model on its pipeline-refined reasoning traces yields human-aligned performance comparable to commercial models like Gemini-2.5-Flash.