Sora视频生成模型30篇相关论文集合！《视频生成模型作为世界模拟器》中引用的所有论文集合

OpenAI 的首个视频生成模型 Sora，让「一句话生成视频」的前沿 AI 技术向上突破了一大截，引发了业界对于生成式 AI 技术方向的大讨论。

OpenAI 探索了视频数据生成模型的大规模训练。具体来说，研究人员在可变持续时间、分辨率和宽高比的视频和图像上联合训练了一个文本条件扩散模型。作者利用对视频和图像潜在代码的时空补丁进行操作的 transformer 架构，其最大的模型 Sora 能够生成长达一分钟的高质量视频。

OpenAI 认为，新展示的结果表明，扩展视频生成模型是构建物理世界通用模拟器的一条有前途的途径。

• Unsupervised Learning of Video Representations using LSTMs

  Paper • 1502.04681 •Published Feb 17, 2015

• Recurrent Environment Simulators

  Paper • 1704.02254 •Published Apr 7, 2017

• World Models

  Paper • 1803.10122 •Published Mar 27, 2018

• Generating Videos with Scene Dynamics

  Paper • 1609.02612 •Published Sep 9, 2016

• MoCoGAN: Decomposing Motion and Content for Video Generation

  Paper • 1707.04993 •Published Jul 17, 2017

• Adversarial Video Generation on Complex Datasets

  Paper • 1907.06571 •Published Jul 16, 2019

• Generating Long Videos of Dynamic Scenes

  Paper • 2206.03429 •Published Jun 8, 2022

• VideoGPT: Video Generation using VQ-VAE and Transformers

  Paper • 2104.10157 •Published Apr 21, 2021 • 2

• NÜWA: Visual Synthesis Pre-training for Neural visUal World creAtion

  Paper • 2111.12417 •Published Nov 24, 2021

• Imagen Video: High Definition Video Generation with Diffusion Models

  Paper • 2210.02303 •Published Oct 5, 2022

• Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models

  Paper • 2304.08818 •Published Apr 18, 2023 • 4

• Photorealistic Video Generation with Diffusion Models

  Paper • 2312.06662 •Published Dec 12, 2023 • 20

• Language Models are Few-Shot Learners

  Paper • 2005.14165 •Published May 29, 2020 • 7

• An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale

  Paper • 2010.11929 •Published Oct 23, 2020 • 2

• ViViT: A Video Vision Transformer

  Paper • 2103.15691 •Published Mar 29, 2021

• Masked Autoencoders Are Scalable Vision Learners

  Paper • 2111.06377 •Published Nov 12, 2021 • 1

• Patch n' Pack: NaViT, a Vision Transformer for any Aspect Ratio and Resolution

  Paper • 2307.06304 •Published Jul 13, 2023 • 23

• High-Resolution Image Synthesis with Latent Diffusion Models

  Paper • 2112.10752 •Published Dec 21, 2021 • 5

• Auto-Encoding Variational Bayes

  Paper • 1312.6114 •Published Dec 21, 2013

• Deep Unsupervised Learning using Nonequilibrium Thermodynamics

  Paper • 1503.03585 •Published Mar 12, 2015

• Denoising Diffusion Probabilistic Models

  Paper • 2006.11239 •Published Jun 20, 2020 • 1

• Improved Denoising Diffusion Probabilistic Models

  Paper • 2102.09672 •Published Feb 19, 2021 • 1

• Diffusion Models Beat GANs on Image Synthesis

  Paper • 2105.05233 •Published May 12, 2021

• Elucidating the Design Space of Diffusion-Based Generative Models

  Paper • 2206.00364 •Published Jun 1, 2022 • 1

• Scalable Diffusion Models with Transformers

  Paper • 2212.09748 •Published Dec 20, 2022 • 4

• Zero-Shot Text-to-Image Generation