# MovieGrid：面向长视频多镜头生成的多网格后训练范式

- 来源：HuggingFace Daily Papers（社区热门论文）
- 发布时间：2026-09-06 08:00
- AIHOT 分数：47
- AIHOT 链接：https://aihot.news/items/cmttkjroo0cb2rofphydvtzl1
- 原文链接：https://arxiv.org/abs/2609.06373

## AI 摘要

MovieGrid提出多网格后训练范式，将长视频分解为按时间排序的短片段并排列在空间网格上联合建模，减少每个时间轴处理的镜头数并支持跨片段信息交换。基于1,000个长视频构建的MGLV数据集产出54K网格视频，在相同token预算下，MovieGrid生成的镜头数是Temporal Packing的6.05倍。

## 正文

Generating long-form multi-shot videos requires coherent within-shot motion and visually consistent narratives across shots. Existing video generators favor continuous motion and struggle to present complete shot sets when an entire narrative is packed along one temporal axis. We propose MovieGrid, a Multi-Grid Post-Training paradigm that decomposes a long video into shorter, temporally ordered chunks and arranges them on a spatial grid for joint modeling. This design reduces the number of shots handled by each temporal axis while enabling global information exchange across chunks. We construct the Multi-Grid Long Video (MGLV) dataset from 1,000 long-form videos using source video collection, hierarchical segmentation, grid video construction, and character-aware story annotation, producing 54K grid videos paired with story prompts. Our Noise-Free Random-Grid Training retains a random subset of chunks as clean visual context for denoising the remaining chunks. Grid Embedding encodes grid structure, character-aware Story Prompts link recurring entities, and Grid Boundary Loss stabilizes layouts. Under the same token budget, MovieGrid generates 6.05 times more shots than Temporal Packing in a 1,616-frame video. On a benchmark spanning five real-world categories, it achieves state-of-the-art intra-shot consistency (0.9131 versus 0.8086 for HoloCine) and inter-shot consistency (0.5914 versus 0.5384 for StoryMem). MovieGrid can further scale video length with minimal compromise through single or multiple generations.