Saved in:
Bibliographic Details
Main Authors: Zhang, Yuang, Cheng, Junqi, Zhao, Haoyu, Gu, Jiaxi, Zou, Fangyuan, Lu, Zenghui, Shu, Peng
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2508.07597
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911105992884224
author Zhang, Yuang
Cheng, Junqi
Zhao, Haoyu
Gu, Jiaxi
Zou, Fangyuan
Lu, Zenghui
Shu, Peng
author_facet Zhang, Yuang
Cheng, Junqi
Zhao, Haoyu
Gu, Jiaxi
Zou, Fangyuan
Lu, Zenghui
Shu, Peng
contents Over-the-shoulder dialogue videos are essential in films, short dramas, and advertisements, providing visual variety and enhancing viewers' emotional connection. Despite their importance, such dialogue scenes remain largely underexplored in video generation research. The main challenges include maintaining character consistency across different shots, creating a sense of spatial continuity, and generating long, multi-turn dialogues within limited computational budgets. Here, we present ShoulderShot, a framework that combines dual-shot generation with looping video, enabling extended dialogues while preserving character consistency. Our results demonstrate capabilities that surpass existing methods in terms of shot-reverse-shot layout, spatial continuity, and flexibility in dialogue length, thereby opening up new possibilities for practical dialogue video generation. Videos and comparisons are available at https://shouldershot.github.io.
format Preprint
id arxiv_https___arxiv_org_abs_2508_07597
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ShoulderShot: Generating Over-the-Shoulder Dialogue Videos
Zhang, Yuang
Cheng, Junqi
Zhao, Haoyu
Gu, Jiaxi
Zou, Fangyuan
Lu, Zenghui
Shu, Peng
Computer Vision and Pattern Recognition
Artificial Intelligence
Over-the-shoulder dialogue videos are essential in films, short dramas, and advertisements, providing visual variety and enhancing viewers' emotional connection. Despite their importance, such dialogue scenes remain largely underexplored in video generation research. The main challenges include maintaining character consistency across different shots, creating a sense of spatial continuity, and generating long, multi-turn dialogues within limited computational budgets. Here, we present ShoulderShot, a framework that combines dual-shot generation with looping video, enabling extended dialogues while preserving character consistency. Our results demonstrate capabilities that surpass existing methods in terms of shot-reverse-shot layout, spatial continuity, and flexibility in dialogue length, thereby opening up new possibilities for practical dialogue video generation. Videos and comparisons are available at https://shouldershot.github.io.
title ShoulderShot: Generating Over-the-Shoulder Dialogue Videos
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2508.07597