Empirical and Comparative Study of Long-Sequence Video Consistency in AIGC

AIGC 장시간 시퀀스 영상 일관성 실증 및 비교연구

초록

With the rise of generative AI, AI-based video synthesis has emerged as a transformative tool in film, advertising, and new media. However, complex scenes continue to face challenges, such as temporal discontinuity, lack of physical consistency, and style shifts. This study conducts a comparative analysis of JiMeng, Vidu, and Keling AI across six scenarios: forest/animals, city/street, indoor/people, beach/nature, sci-fi/city, and product/exhibition. Using unified prompts and a standardized frame-continuity strategy, 5-s videos (16:9) were generated under default settings. Results show that JiMeng performs best in urban, sci-fi, and product scenes; Keling excels in natural environments; and Vidu stands out in indoor character expressions. This study proposes a platform evaluation paradigm and highlights scenario-specific strengths, providing essential technical guidance for creative applications in the AI-driven media landscape.

키워드

AI Video Generation; Content Coherence; Physical Consistency; Style Stability; Sequential Video; AI 영상 생성; 내용 연속성; 물리적 일관성; 스타일 안정성; 연속 영상
제목
Empirical and Comparative Study of Long-Sequence Video Consistency in AIGC
제목 (타언어)
AIGC 장시간 시퀀스 영상 일관성 실증 및 비교연구
저자
장예한; 선심이; 정진헌
DOI
10.9728/dcs.2026.27.2.347
발행일
2026-02
유형
Y
저널명
디지털콘텐츠학회논문지
권
27
호
2
페이지
347 ~ 356