![[2502.17863] A Survey: Spatiotemporal Consistency in Video Generation](https://arxiv.org/static/browse/0.3.4/images/arxiv-logo-fb.png){kind=logo}
[2502.17863] A Survey: Spatiotemporal Consistency in Video Generation
Summary
This survey reviews advancements in spatiotemporal consistency in video generation, addressing challenges and methodologies in creating coherent video sequences.
Why It Matters
As video generation technology evolves, ensuring spatiotemporal consistency is crucial for producing high-quality, coherent visual content. This survey fills a gap in the literature by systematically reviewing existing methods and exploring future research directions, making it a valuable resource for researchers and practitioners in AI and computer vision.
Key Takeaways
- Spatiotemporal consistency is essential for coherent video generation.
- The paper reviews various models, frameworks, and evaluation metrics in the field.
- Future research directions are discussed, highlighting ongoing challenges.
- The survey provides insights into training strategies and post-processing techniques.
- Systematic reviews on this topic are scarce, making this paper a significant contribution.
Computer Science > Computer Vision and Pattern Recognition arXiv:2502.17863 (cs) [Submitted on 25 Feb 2025 (v1), last revised 18 Feb 2026 (this version, v2)] Title:A Survey: Spatiotemporal Consistency in Video Generation Authors:Zhiyu Yin, Kehai Chen, Xuefeng Bai, Ruili Jiang, Juntao Li, Hongdong Li, Jin Liu, Yang Xiang, Jun Yu, Min Zhang View a PDF of the paper titled A Survey: Spatiotemporal Consistency in Video Generation, by Zhiyu Yin and 8 other authors View PDF HTML (experimental) Abstract:Video generation aims to produce temporally coherent sequences of visual frames, representing a pivotal advancement in Artificial Intelligence Generated Content (AIGC). Compared to static image generation, video generation poses unique challenges: it demands not only high-quality individual frames but also strong temporal coherence to ensure consistency throughout the spatiotemporal sequence. Although research addressing spatiotemporal consistency in video generation has increased in recent years, systematic reviews focusing on this core issue remain relatively scarce. To fill this gap, this paper views the video generation task as a sequential sampling process from a high-dimensional spatiotemporal distribution, and further discusses spatiotemporal consistency. We provide a systematic review of the latest advancements in the field. The content spans multiple dimensions including generation models, feature representations, generation frameworks, post-processing techniques, training...