arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2008.09646eess.IVcs.CVcs.LG
收藏

HRVGAN:使用时空生成对抗网络的高分辨率视频生成

HRVGAN: High Resolution Video Generation using Spatio-Temporal GAN

University of Maryland(马里兰大学);College Park, Maryland

Abhinav Sagar

AI总结:

本文提出HRVGAN,结合WGAN的k-Lipschitz约束和cGAN的类别条件,用于高分辨率视频生成,并在UCF101等数据集上以IS和FID指标显著超越现有无监督方法。

摘要:

高分辨率视频生成已成为计算机视觉中的一项关键任务,在娱乐、仿真和数据增强等领域具有广泛应用。然而,由于视频数据的高维性和复杂动态特性,生成时间上连贯且视觉上逼真的视频仍然是一个重大挑战。本文提出了一种专为高分辨率视频合成设计的新型深度生成网络架构。我们的方法融合了Wasserstein生成对抗网络(WGAN)的核心思想,对判别器施加k-Lipschitz连续性约束以稳定训练并增强收敛性。我们进一步利用条件生成对抗网络(cGAN)技术,在训练和推理过程中引入类别标签,从而实现具有更好语义一致性的特定类别视频生成。我们给出了生成器和判别器网络的逐层详细描述,重点说明了促进时间连贯性和空间细节的架构设计选择。整体组合架构、训练算法和优化策略均得到了完整呈现。我们的训练目标将逐像素均方误差损失与对抗损失相结合,以平衡帧级精度和视频真实感。我们在包括UCF101、Golf和Aeroplane在内的基准数据集上验证了所提方法,这些数据集涵盖了多样的运动模式和场景上下文。使用Inception Score(IS)和Fréchet Inception Distance(FID)进行的定量评估表明,我们的模型在质量和多样性方面均显著优于以往最先进的无监督视频生成方法。

英文摘要:

High-resolution video generation has emerged as a crucial task in computer vision, with wide-ranging applications in entertainment, simulation, and data augmentation. However, generating temporally coherent and visually realistic videos remains a significant challenge due to the high dimensionality and complex dynamics of video data. In this paper, we propose a novel deep generative network architecture designed specifically for high-resolution video synthesis. Our approach integrates key concepts from Wasserstein Generative Adversarial Networks (WGANs), enforcing a k-Lipschitz continuity constraint on the discriminator to stabilize training and enhance convergence. We further leverage Conditional GAN (cGAN) techniques by incorporating class labels during both training and inference, enabling class-specific video generation with improved semantic consistency. We provide a detailed layer-wise description of the Generator and Discriminator networks, highlighting architectural design choices promoting temporal coherence and spatial detail. The overall combined architecture, training algorithm, and optimization strategy are thoroughly presented. Our training objective combines a pixel-wise mean squared error loss with an adversarial loss to balance frame-level accuracy and video realism. We validate our approach on benchmark datasets including UCF101, Golf, and Aeroplane, encompassing diverse motion patterns and scene contexts. Quantitative evaluations using Inception Score (IS) and Fréchet Inception Distance (FID) demonstrate that our model significantly outperforms previous state-of-the-art unsupervised video generation methods in terms of both quality and diversity.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑