Autoregressive Video Generation without Vector Quantization

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Deng, Haoge, Pan, Ting, Diao, Haiwen, Luo, Zhengxiong, Cui, Yufeng, Lu, Huchuan, Shan, Shiguang, Qi, Yonggang, Wang, Xinlong
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912254593597440
author Deng, Haoge
Pan, Ting
Diao, Haiwen
Luo, Zhengxiong
Cui, Yufeng
Lu, Huchuan
Shan, Shiguang
Qi, Yonggang
Wang, Xinlong
author_facet Deng, Haoge
Pan, Ting
Diao, Haiwen
Luo, Zhengxiong
Cui, Yufeng
Lu, Huchuan
Shan, Shiguang
Qi, Yonggang
Wang, Xinlong
contents This paper presents a novel approach that enables autoregressive video generation with high efficiency. We propose to reformulate the video generation problem as a non-quantized autoregressive modeling of temporal frame-by-frame prediction and spatial set-by-set prediction. Unlike raster-scan prediction in prior autoregressive models or joint distribution modeling of fixed-length tokens in diffusion models, our approach maintains the causal property of GPT-style models for flexible in-context capabilities, while leveraging bidirectional modeling within individual frames for efficiency. With the proposed approach, we train a novel video autoregressive model without vector quantization, termed NOVA. Our results demonstrate that NOVA surpasses prior autoregressive video models in data efficiency, inference speed, visual fidelity, and video fluency, even with a much smaller model capacity, i.e., 0.6B parameters. NOVA also outperforms state-of-the-art image diffusion models in text-to-image generation tasks, with a significantly lower training cost. Additionally, NOVA generalizes well across extended video durations and enables diverse zero-shot applications in one unified model. Code and models are publicly available at https://github.com/baaivision/NOVA.
format Preprint
id arxiv_https___arxiv_org_abs_2412_14169
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Autoregressive Video Generation without Vector Quantization
Deng, Haoge
Pan, Ting
Diao, Haiwen
Luo, Zhengxiong
Cui, Yufeng
Lu, Huchuan
Shan, Shiguang
Qi, Yonggang
Wang, Xinlong
Computer Vision and Pattern Recognition
This paper presents a novel approach that enables autoregressive video generation with high efficiency. We propose to reformulate the video generation problem as a non-quantized autoregressive modeling of temporal frame-by-frame prediction and spatial set-by-set prediction. Unlike raster-scan prediction in prior autoregressive models or joint distribution modeling of fixed-length tokens in diffusion models, our approach maintains the causal property of GPT-style models for flexible in-context capabilities, while leveraging bidirectional modeling within individual frames for efficiency. With the proposed approach, we train a novel video autoregressive model without vector quantization, termed NOVA. Our results demonstrate that NOVA surpasses prior autoregressive video models in data efficiency, inference speed, visual fidelity, and video fluency, even with a much smaller model capacity, i.e., 0.6B parameters. NOVA also outperforms state-of-the-art image diffusion models in text-to-image generation tasks, with a significantly lower training cost. Additionally, NOVA generalizes well across extended video durations and enables diverse zero-shot applications in one unified model. Code and models are publicly available at https://github.com/baaivision/NOVA.
title Autoregressive Video Generation without Vector Quantization
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2412.14169