PersonaShot: Benchmarking Person-Centric Narrative Continuity in Multi-Shot Video Generation
2026-08-17 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors created PersonaShot, a new benchmark to test how well video generation models keep a character's appearance, emotions, and story consistent across multiple shots in a video. Unlike previous tests that looked only at single clips, their benchmark checks continuity over different time scales and story levels. They designed special evaluators aligned with human experts to measure specific aspects like physical state and emotional flow. Their tests showed that even advanced models often struggle to keep these details smooth and connected across shots. This work highlights gaps between visual quality and story consistency in generated videos.
video generationmulti-shot narrativecharacter coherencephysical continuityaffective dynamicscinematic grammarbenchmark evaluationmultimodal learninghuman-aligned evaluationnarrative continuity
Authors
Yuji Wang, Yuheng Chen, Teng Hu, Ran Yi, Yijia Hong, Han Feng, Weijian Cao, Chengjie Wang, Lizhuang Ma, Jiangning Zhang
Abstract
Video generation is rapidly evolving from single-shot clips to multi-shot narratives, where the human character serves as the core narrative anchor. However, existing benchmarks mainly assess character appearance or individual-shot quality, without measuring whether physical and emotional states remain coherent across cuts. They also rarely provide criterion-specific evaluation methods, although physical continuity, facial dynamics, and cinematic relations require different visual, temporal, and relational evidence. To address these limitations, we introduce PersonaShot, the first person-centric benchmark for narrative continuity in multi-shot video generation. PersonaShot contains approximately 1,000 multi-shot segments and 16 metrics spanning physical continuity, affective dynamics, and cinematic grammar. \textbf{\textit{1)} Narrative Continuity Benchmark:} We evaluate character coherence across three temporal levels: within-shot states, cross-shot transitions, and sequence-level trajectories. \textbf{\textit{2)} Human-Aligned Specialist Evaluators:} We distill reasoning from a large multimodal teacher into lightweight criterion-specific evaluators, each grounded in the visual, temporal, or relational evidence required by its metric, and align them with expert human judgments. \textbf{\textit{3)} Systematic Evaluation and Insights:} Our evaluation reveals distinct capability profiles across state-of-the-art models and a clear gap between perceptual quality and cross-shot narrative continuity. Even visually compelling videos frequently exhibit physical-state resets, abrupt affective shifts, and broken cinematic relations across shots. Human studies further demonstrate strong agreement between our evaluators and expert judgments.