mlsanityData to 7 Oct 2026

VideoFlow: A Conditional Flow-Based Model for Stochastic Video Generation

arXiv 1903.01434 ↗First posted 4 Mar 2019cs.CV cs.AI cs.LGcited by 74

Not on the map. Why?

Abstract (arXiv)

Generative models that can model and predict sequences of future events can, in principle, learn to capture complex real-world phenomena, such as physical interactions. However, a central challenge in video prediction is that the future is highly uncertain: a sequence of past observations of events can imply many possible futures. Although a number of recent works have studied probabilistic models that can represent uncertain futures, such models are either extremely expensive computationally as in the case of pixel-level autoregressive models, or do not directly optimize the likelihood of the data. To our knowledge, our work is the first to propose multi-frame video prediction with normalizing flows, which allows for direct optimization of the data likelihood, and produces high-quality stochastic predictions. We describe an approach for modeling the latent space dynamics, and demonstrate that flow-based generative models offer a viable and competitive approach to generative modelling of video.

Key facts. Cited by 74 papers in the map (data through 7 Oct 2026). First posted on arXiv 4 Mar 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 26; 2022: 20; 2023: 9; 2024: 7; 2025: 7; 2026: 5.

74 papers.

Sort:

By area:

  1. 2022Imagen Video: High Definition Video Generation with Diffusion Modelscited by 1,765
  2. 2022MagicVideo: Efficient Video Generation With Latent Diffusion Modelscited by 463
  3. 2022Latent Video Diffusion Models for High-Fidelity Long Video Generationcited by 385
  4. 2023Driving into the Future: Multiview Visual Forecasting and Planning with World Model for Autonomous Drivingcited by 309
  5. 2021CLIP-Forge: Towards Zero-Shot Text-to-Shape Generationcited by 254
  6. 2023Emu Video: Factorizing Text-to-Video Generation by Explicit Image Conditioningcited by 254
  7. 2021N"UWA: Visual Synthesis Pre-training for Neural visUal World creAtioncited by 253
  8. 2022Long Video Generation with Time-Agnostic VQGAN and Time-Sensitive Transformercited by 244
  9. 2022Generating Videos with Dynamics-aware Implicit Generative Adversarial Networkscited by 186
  10. 2022Generating Long Videos of Dynamic Scenescited by 113
  11. 2021CCVS: Context-aware Controllable Video Synthesiscited by 68
  12. 2021Playable Video Generationcited by 63
38 more
  1. 2021Predicting Video with VQVAEcited by 61
  2. 2022Efficient Video Prediction via Sparsely Conditioned Flow Matchingcited by 54
  3. 2021Stochastic Image-to-Video Synthesis using cINNscited by 49
  4. 2021Learning the Predictability of the Futurecited by 48
  5. 2022A Tale of Two Flows: Cooperative Learning of Langevin Flow and Normalizing Flow Toward Energy-Based Modelcited by 44
  6. 2021iPOKE: Poking a Still Image for Controlled Stochastic Video Synthesiscited by 42
  7. 2024Efficient Video Diffusion Models via Content-Frame Motion-Latent Decompositioncited by 41
  8. 2021Clockwork Variational Autoencoderscited by 40
  9. 2021Understanding Object Dynamics for Interactive Image-to-Video Synthesiscited by 38
  10. 2023Dysen-VDM: Empowering Dynamics-aware Text-to-Video Diffusion with LLMscited by 35
  11. 2025Free4D: Tuning-free 4D Scene Generation with Spatial-Temporal Consistencycited by 34
  12. 2023Feature-Conditioned Cascaded Video Diffusion Models for Precise Echocardiogram Synthesiscited by 32
  13. 2022Playable Environments: Video Manipulation in Space and Timecited by 29
  14. 2023The Treasure Beneath Multiple Annotations: An Uncertainty-aware Edge Detectorcited by 25
  15. 2021Transflower: probabilistic autoregressive dance generation with multimodal attentioncited by 22
  16. 2021VisuoSpatial Foresight for Physical Sequential Fabric Manipulationcited by 18
  17. 2022Target-aware Molecular Graph Generationcited by 18
  18. 2021Diverse Video Generation using a Gaussian Process Triggercited by 17
  19. 2022Invertible Rescaling Network and Its Extensionscited by 15
  20. 2025Synthetic Video Enhances Physical Fidelity in Video Synthesiscited by 15
  21. 2025MALT Diffusion: Memory-Augmented Latent Transformers for Any-Length Video Generationcited by 14
  22. 2021Learning Temporal Dynamics from Cycles in Narrated Videocited by 13
  23. 2021Accurate Grid Keypoint Learning for Efficient Video Predictioncited by 13
  24. 2022STGlow: A Flow-based Generative Framework with Dual Graphormer for Pedestrian Trajectory Predictioncited by 13
  25. 2023Sign Language Production with Latent Motion Transformercited by 13
  26. 2024Benchmarking Multi-dimensional AIGC Video Quality Assessment: A Dataset and Unified Modelcited by 13
  27. 2022Towards Smooth Video Compositioncited by 12
  28. 2021Future Frame Prediction for Robot-assisted Surgerycited by 11
  29. 2021Click to Move: Controlling Video Generation with Sparse Motioncited by 11
  30. 2022Gradual Domain Adaptation via Normalizing Flowscited by 11
  31. 2021Variational Predictive Routing with Nested Subjective Timescalescited by 9
  32. 2021S3RP: Self-Supervised Super-Resolution and Prediction for Advection-Diffusion Processcited by 9
  33. 2025STARFlow-V: End-to-End Video Generative Modeling with Normalizing Flowscited by 9
  34. 2021Layered Controllable Video Generationcited by 7
  35. 2022Multi-Horizon Representations with Hierarchical Forward Models for Reinforcement Learningcited by 7
  36. 2022Distributional Drift Adaptation with Temporal Conditional Variational Autoencoder for Multivariate Time Series Forecastingcited by 7
  37. 2023A Tale of Two Latent Flows: Learning Latent Space Normalizing Flow with Short-run Langevin Flow for Approximate Inferencecited by 7
  38. 2024Review for Handling Missing Data with special missing mechanismcited by 7

50 most cited of 74 All 74 (JSON)