将视频建模为连续多维过程，提升预测效率与质量
Continuous Video Process: Modeling Videos as Continuous Multi-Dimensional Processes for Video Prediction
- 把视频看作连续动态过程，而非离散帧序列
- 采样步数减少75%，推理更高效
- 在多个基准数据集上达到领先性能
扩散模型在图像生成领域已取得显著进展，涵盖无条件图像合成、文本到图像转换及图像到图像映射等任务。然而，在视频预测方面仍显不足，主要因其将视频视为独立图像的集合，依赖时间注意力等外部机制来保证时序一致性。本文提出一种新模型类别，将视频视为连续多维过程，而非离散帧序列。实验表明，该方法可减少75%的采样步数，显著提升推理效率。在KTH、BAIR、Human3.6M和UCF101等多个基准数据集上均实现当前最优性能。更多视频结果详见项目页面：https://www.cs.umd.edu/~gauravsh/cvp/supp/website.html。
原文摘要 · Abstract (English)
Diffusion models have made significant strides in image generation, mastering tasks such as unconditional image synthesis, text-image translation, and image-to-image conversions. However, their capability falls short in the realm of video prediction, mainly because they treat videos as a collection of independent images, relying on external constraints such as temporal attention mechanisms to enforce temporal coherence. In our paper, we introduce a novel model class, that treats video as a continuous multi-dimensional process rather than a series of discrete frames. We also report a reduction of 75\% sampling steps required to sample a new frame thus making our framework more efficient during the inference time. Through extensive experimentation, we establish state-of-the-art performance in video prediction, validated on benchmark datasets including KTH, BAIR, Human3.6M, and UCF101. Navigate to the project page https://www.cs.umd.edu/~gauravsh/cvp/supp/website.html for video results.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。