paper survey

base model

• [VDM] Video Diffusion Models

  (2022.04.07) NIPS 2022 Google

  [page] [paper] [code]

• MCVD：Masked conditional video diffusion for prediction, generation, and interpolation

  (2022.05.19) NIPS 2022

  [page] [paper] [code]

• [FDM] Flexible Diffusion Modeling of Long Videos

  (2022.05.23) arXiv

  [page] [paper] [code]

• CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers Paper

  (2022.05.29) ICLR 2023 THU

  [page] [paper] [code]

• Make-A-Video：Text-to-Video Generation without Text-Video Data

  (2022.09.29) ICLR 2023 Meta

  [page] [paper] [code]

• IMAGEN VIDEO: HIGH DEFINITION VIDEO GENERATION WITH DIFFUSION MODELS

  (2022.10.05) arXiv Google

  [page] [paper] [code]

• [PVDM] Video Probabilistic Diffusion Models in Projected Latent Space

  (2023.02.15) CVPR 2023 Google

  [page] [paper] [code]

• MagicVideo: Efficient Video Generation With Latent Diffusion Models

  (2022.11.20) arXiv ByteDance

  [page] [paper] [code]

• LVDM：Latent Video Diffusion Models for High-Fidelity Long Video Generation

  (2022.11.23) arXiv HKUST Tencent

  [page] [paper] [code]

• VideoFusion: Decomposed Diffusion Models for High-Quality Video Generation

  (2023.3.15) CVPR 2023 Alibaba UCAS

  [page] [paper] [code]

video editing

• Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation

  (2022.12.22) arXiv Tencent(PCG) NUS

  [page] [paper] [code]

• Shape-aware Text-driven Layered Video Editing

  (2023.1.30) CVPR 2023 University of Maryland

  [page] [paper] [code]

• Gen-1: Structure and Content-Guided Video Synthesis with Diffusion Models

  (2023.2.6) arXiv Runway

  [page] [paper] [code]

• Video-P2P: Video Editing with Cross-attention Control

  (2023.3.8) arXiv Adobe CUHK

  [page] [paper] [code]

• FateZero: Fusing Attentions for Zero-shot Text-based Video Editing

  (2023.3.16) ICCV 2023 Tencent(AI Lab) HKUST

  [page] [paper] [code]

• Pix2video: Video editing using image diffusion

  (2023.3.22) ICCV 2023 Adobe

  [page] [paper] [code]

• Text2video-zero: Text-toimage diffusion models are zero-shot video generators.

  (2023.3.23) arXiv Picsart

  [page] [paper] [code]

• vid2vid-zero: Zero-Shot Video Editing Using Off-The-Shelf Image Diffusion Models

  (2023.3.30) arXiv BAAI ZJU

  [page] [paper] [code]

• ControlVideo: Training-free Controllable Text-to-Video Generation

  (2023.5.22) arXiv Huawei HIT

  [page] [paper] [code]

• ControlVideo: Adding Conditional Control for One Shot Text-to-Video Editing

  (2023.5.26) arXiv Tsinghua

  [page] [paper] [code]

• Gen-L-Video: Multi-Text to Long Video Generation via Temporal Co-Denoising

  (2023.5.29) arXiv Shanghai AI Lab CUHK(mmLab)

  [page] [paper] [code]

• Rerender A Video: Zero-Shot Text-Guided Video-to-Video Translation

  (2023.6.13) arXiv NTU

  [page] [paper] [code]

• VidEdit: Zero-shot and Spatially Aware Text-driven Video Editing

  (2023.6.14) arXiv Paris, France

  [page] [paper] [code]

• TokenFlow: Consistent Diffusion Features for Consistent Video Editing

  (2023.7.19) arXiv Weizmann Institute of Science

  [page] [paper] [code coming]

• VideoControlNet: A Motion-Guided Video-to-Video Translation Framework by Using Diffusion Model with ControlNet

  (2023.7.26) arXiv Beihang University, University of Hong Kong

  [page] [paper] [code coming]