VidTok
📌 核心贡献
本文提出了 VidTok，针对VidTok: A Versatile and Open-Source Vide… 方向进行研究，提出了新颖的方法并在相关基准上取得了优异性能。
📖 摘要
Encoding video content into compact latent tokens has become a fundamental step in video generation and understanding, driven by the need to address the inherent redundancy in pixel-level representations. Consequently, there is a growing demand for high-performance, open-source video tokenizers as video-centric research gains prominence. We introduce VidTok, a versatile video tokenizer that delivers state-of-the-art performance in both continuous and discrete tokenizations. VidTok incorporates several key advancements over existing approaches: 1) model architecture such as convolutional layers and up/downsampling modules; 2) to address the training instability and codebook collapse commonly associated with conventional Vector Quantization (VQ), we integrate Finite Scalar Quantization (FSQ) into discrete video tokenization; 3) improved training strategies, including a two-stage training process and the use of reduced frame rates. By integrating these advancements, VidTok achieves substantial improvements over existing methods, demonstrating superior performance across multiple metrics, including PSNR, SSIM, LPIPS, and FVD, under standardized evaluation settings.
🔍 关键信息
| 字段 | 内容 |
|---|---|
| 机构 | |
| 发表 | 2024-12-17 |
| 分类 | cs.CV |
| 链接 | arXiv |