VidTok: A Versatile and Open-Source Video Tokenizer

Autor:	Tang, Anni, He, Tianyu, Guo, Junliang, Cheng, Xinle, Song, Li, Bian, Jiang
Rok vydání:	2024
Předmět:	Computer Science - Computer Vision and Pattern Recognition Computer Science - Artificial Intelligence Computer Science - Machine Learning
Druh dokumentu:	Working Paper
Popis:	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. Comment: Code & Models: https://github.com/microsoft/VidTok
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2412.13061 Zobrazit plný text záznamu View this record from Arxiv