LogiShot: Logically Coherent Cross-Shot Video Generation

2026-08-09

AI Summary

This work addresses the challenges of narrative incoherence and visual inconsistency in cross-shot video generation caused by ambiguous user instructions. To this end, the authors propose a conditional video generation method that integrates multimodal context joint encoding with an explicit visual memory mechanism. By densely fusing video context with other conditioning signals and maintaining visual memory throughout the generation process, the approach ensures dual coherence—both semantic-logical and visual—across multiple shots. As the first study to incorporate a visual memory mechanism into conditional video generation, this method significantly outperforms existing baselines on a newly curated dataset of 110,000 samples, demonstrating particularly strong improvements on metrics evaluating cross-shot logical coherence.

Abstract

Generating cross-shot videos that are logically connected is essential for content creation. Currently, most cross-shot video-generation workflows, such as short-drama production, still rely on isolated textual scripts or explicit reference images to specify the generated content. Consequently, when user instructions are underspecified or ambiguous, a generated clip may appear visually plausible on its own but fail to align with the overall narrative, leading to disjointed content. We argue that achieving cross-shot logical coherence in video generation requires establishing logical connections across shots and maintaining visual consistency. To this end, we propose LogiShot, which incorporates information through two complementary paths: 1) LogiShot jointly encodes the context video and other conditioning signals, yielding dense multimodal cues that provide visual-semantic evidence for cross-shot generation; 2) the model maintains a visual memory of the context video throughout generation to preserve visual consistency across shots. Additionally, we construct a dataset with 110K samples and a dedicated benchmark for evaluating cross-shot logical coherence. Experiments demonstrate that LogiShot consistently outperforms existing baselines in terms of logical coherence across multiple shots. Model and data will be made publicly available.

Problem

• cross-shot video generation
• logical coherence
• visual consistency
• narrative alignment
• video generation

Innovation

• cross-shot video generation
• logical coherence
• visual consistency
• multimodal cues
• visual memory