mlsanityData to 7 Oct 2026

A Survey on Long Video Generation: Challenges, Methods, and Prospects

arXiv 2403.16407 ↗First posted 25 Mar 2024cs.CVcited by 40

Not on the map. Why?

Abstract (arXiv)

Video generation is a rapidly advancing research area, garnering significant attention due to its broad range of applications. One critical aspect of this field is the generation of long-duration videos, which presents unique challenges and opportunities. This paper presents the first survey of recent advancements in long video generation and summarises them into two key paradigms: divide and conquer temporal autoregressive. We delve into the common models employed in each paradigm, including aspects of network design and conditioning techniques. Furthermore, we offer a comprehensive overview and classification of the datasets and evaluation metrics which are crucial for advancing long video generation research. Concluding with a summary of existing studies, we also discuss the emerging challenges and future directions in this dynamic field. We hope that this survey will serve as an essential reference for researchers and practitioners in the realm of long video generation.

Key facts. Cited by 40 papers in the map (data through 7 Oct 2026). Builds on 38 of its 48 references that are in the map. First posted on arXiv 25 Mar 2024.

Builds on

38 of 48 references.

References · 38

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  4. 2016Improved Techniques for Training GANscited by 2,938
  5. 2023Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Modelscited by 1,465
  6. 2018Towards Accurate Generative Models of Video: A New Metric & Challengescited by 1,204
  7. 2021Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrievalcited by 1,175
  8. 2022CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformerscited by 973
  9. 2020First Order Motion Model for Image Animationcited by 698
  10. 2017Generative Adversarial Networks: An Overviewcited by 588
  11. 2013Generating Sequences With Recurrent Neural Networkscited by 549
  12. 2023VideoPoet: A Large Language Model for Zero-Shot Video Generationcited by 479
26 more
  1. 2022Phenaki: Variable Length Video Generation From Open Domain Textual Descriptioncited by 475
  2. 2018A Short Note about Kinetics-600cited by 331
  3. 2023VideoFusion: Decomposed Diffusion Models for High-Quality Video Generationcited by 330
  4. 2022MCVD: Masked Conditional Video Diffusion for Prediction, Generation, and Interpolationcited by 307
  5. 2021StyleGAN-V: A Continuous Video Generator with the Price, Image Quality and Perks of StyleGAN2cited by 300
  6. 2022Flexible Diffusion Modeling of Long Videoscited by 294
  7. 2022Long Video Generation with Time-Agnostic VQGAN and Time-Sensitive Transformercited by 244
  8. 2023SEINE: Short-to-Long Video Diffusion Model for Generative Transition and Predictioncited by 231
  9. 2022Generating Videos with Dynamics-aware Implicit Generative Adversarial Networkscited by 186
  10. 2023Video Probabilistic Diffusion Models in Projected Latent Spacecited by 171
  11. 2023NUWA-XL: Diffusion over Diffusion for eXtremely Long Video Generationcited by 170
  12. 2023Make Pixels Dance: High-Dynamic Video Generationcited by 140
  13. 2023VideoDirectorGPT: Consistent Multi-scene Video Generation via LLM-Guided Planningcited by 138
  14. 2017Self-Supervised Visual Planning with Temporal Skip Connectionscited by 137
  15. 2022Diffusion Models for Video Prediction and Infillingcited by 134
  16. 2023Consistent View Synthesis with Pose-Guided Diffusion Modelscited by 117
  17. 2022Generating Long Videos of Dynamic Scenescited by 113
  18. 2017Learning to Generate Time-Lapse Videos Using Multi-Stage Dynamic Generative Adversarial Networkscited by 88
  19. 2024FiT: Flexible Vision Transformer for Diffusion Modelcited by 84
  20. 2022NUWA-Infinity: Autoregressive over Autoregressive Generation for Infinite Visual Synthesiscited by 71
  21. 2024Vlogger: Make Your Dream A Vlogcited by 70
  22. 2022Look Outside the Room: Synthesizing A Consistent Long-Term 3D Scene Video from A Single Imagecited by 55
  23. 2023Reuse and Diffuse: Iterative Denoising for Text-to-Video Generationcited by 49
  24. 2022Transframer: Arbitrary Frame Prediction with Generative Modelscited by 37
  25. 2023Video Diffusion Models with Local-Global Context Guidancecited by 15
  26. 2023Video Generation Beyond a Single Clipcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 10; 2025: 20; 2026: 10.

40 papers.

Sort:

By area:

  1. 2024FreeLong: Training-Free Long Video Generation with SpectralBlend Temporal Attentioncited by 87
  2. 2024PhyT2V: LLM-Guided Iterative Self-Refinement for Physics-Grounded Text-to-Video Generationcited by 77
  3. 2025It's All Connected: A Journey Through Test-Time Memorization, Attentional Bias, Retention, and Online Optimizationcited by 60
  4. 2025ATLAS: Learning to Optimally Memorize the Context at Test Timecited by 57
  5. 2025Video-T1: Test-Time Scaling for Video Generationcited by 39
  6. 2025Exploring the Evolution of Physics Cognition in Video Generation: A Surveycited by 31
  7. 2024Is Your World Simulator a Good Story Presenter? A Consecutive Events-Based Benchmark for Future Long Video Generationcited by 28
  8. 2024A Comprehensive Survey of Direct Preference Optimization: Datasets, Theories, Variants, and Applicationscited by 27
  9. 2025CineTrans: Learning to Generate Videos with Cinematic Transitions via Masked Diffusion Modelscited by 26
  10. 2024A Comprehensive Survey on Human Video Generation: Challenges, Methods, and Insightscited by 24
  11. 2025Code2Video: A Code-centric Paradigm for Educational Video Generationcited by 23
  12. 2025WorldLens: Full-Spectrum Evaluations of Driving World Models in Real Worldcited by 22
28 more
  1. 2024SurGen: Text-Guided Diffusion Model for Surgical Video Generationcited by 19
  2. 2025MiLA: Multi-view Intensive-fidelity Long-term Video Generation World Model for Autonomous Drivingcited by 18
  3. 2025Generative AI for Cel-Animation: A Surveycited by 17
  4. 2025LongDiff: Training-Free Long Video Generation in One Gocited by 13
  5. 2026Mode Seeking meets Mean Seeking for Fast Long Video Generationcited by 12
  6. 2024Deepfake Media Generation and Detection in the Generative AI Era: A Survey and Outlookcited by 10
  7. 2025FastCar: Cache Attentive Replay for Fast Auto-Regressive Video Generation on the Edgecited by 9
  8. 2025Video-GPT via Next Clip Diffusioncited by 8
  9. 2024Video Is Worth a Thousand Images: Exploring the Latest Trends in Long Video Generationcited by 7
  10. 2026Evolution of Video Generative Foundationscited by 6
  11. 2025ShotDirector: Directorially Controllable Multi-Shot Video Generation with Cinematographic Transitionscited by 5
  12. 2025WaveStitch: Flexible and Fast Conditional Time Series Generation with Diffusion Modelscited by 4
  13. 2025A Survey: Spatiotemporal Consistency in Video Generationcited by 3
  14. 2024Cognitively Inspired Energy-Based World Modelscited by 1
  15. 2025A Self-supervised Motion Representation for Portrait Video Generationcited by 1
  16. 2025Frame-Level Captions for Long Video Generation with Complex Multi Scenescited by 1
  17. 2025PipeDiT: Accelerating Diffusion Transformers in Video Generation with Task Pipelining and Model Decouplingcited by 1
  18. 2026Training-free Motion Factorization for Compositional Video Generationcited by 1
  19. 2026GTA: Advancing Image-to-3D World Generation via Geometry Then Appearance Video Diffusioncited by 1
  20. 2026MSEditor: Toward Consistent Multi-Shot Video Editingcited by 1
  21. 2026SubjectAnchor: Subject-Aware Memory-to-Video for Multi-Shot Storytellingcited by 1
  22. 2024Decoupled Video Generation with Chain of Training-free Diffusion Model Expertscited by 0
  23. 2025SSG-Dit: A Spatial Signal Guided Framework for Controllable Video Generationcited by 0
  24. 2025Inference-based GAN Video Generationcited by 0
  25. 2026VC-Bench: Pioneering the Video Connecting Benchmark with a Dataset and Evaluation Metricscited by 0
  26. 2026DrawVideo: Grounded and Faithful Multi-Shot Video Generation from Storyboard Keyframe Sketchescited by 0
  27. 2026RhymeFlow: Training-Free Acceleration for Video Generation with Asynchronous Denoising Flow Schedulingcited by 0
  28. 2026World Simulator: Queer Erotica and the Absurdity of AI Video Models That Promise the Worldcited by 0