mlsanityData to 7 Oct 2026

Dense Optical Flow Prediction from a Static Image

arXiv 1505.00295 ↗First posted 2 May 2015cs.CVcited by 36

Not on the map. Why?

Abstract (arXiv)

Given a scene, what is going to move, and in what direction will it move? Such a question could be considered a non-semantic form of action prediction. In this work, we present a convolutional neural network (CNN) based approach for motion prediction. Given a static image, this CNN predicts the future motion of each and every pixel in the image in terms of optical flow. Our CNN model leverages the data in tens of thousands of realistic videos to train our model. Our method relies on absolutely no human labeling and is able to predict motion based on the context of the scene. Because our CNN model makes no assumptions about the underlying scene, it can predict future optical flow on a diverse set of scenarios. We outperform all previous approaches by large margins.

Key facts. Cited by 36 papers in the map (data through 7 Oct 2026). First posted on arXiv 2 May 2015.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2019: 1; 2020: 0; 2021: 11; 2022: 8; 2023: 5; 2024: 2; 2025: 6; 2026: 3.

36 papers.

Sort:

By area:

  1. 2021Conditional Object-Centric Learning from Videocited by 247
  2. 2022Diffusion Probabilistic Modeling for Video Generationcited by 237
  3. 2023A Survey on Self-supervised Learning: Algorithms, Applications, and Future Trendscited by 205
  4. 2021NEAT: Neural Attention Fields for End-to-End Autonomous Drivingcited by 174
  5. 2022Diffusion Models for Video Prediction and Infillingcited by 134
  6. 2023Diffusion with Forward Models: Solving Stochastic Inverse Problems Without Direct Supervisioncited by 112
  7. 2023Generative Image Dynamicscited by 93
  8. 2021FitVid: Overfitting in Pixel-Level Video Predictioncited by 86
  9. 2021Greedy Hierarchical Variational Autoencoders for Large-Scale Video Predictioncited by 75
  10. 2024MemFlow: Optical Flow Estimation and Prediction with Memorycited by 55
  11. 2019Imitation Learning for Human Pose Predictioncited by 44
  12. 2021SLAMP: Stochastic Latent Appearance and Motion Predictioncited by 32
24 more
  1. 2022Vision+X: A Survey on Multimodal Learning in the Light of Datacited by 22
  2. 2022Simulating Fluids in Real-World Still Imagescited by 15
  3. 2023A step towards understanding why classification helps regressioncited by 15
  4. 2025Pixel Motion as Universal Representation for Robot Controlcited by 15
  5. 2021Learning Temporal Dynamics from Cycles in Narrated Videocited by 13
  6. 2025General Intelligence Requires Reward-based Pretrainingcited by 12
  7. 2021Dimensions of Motion: Monocular Prediction through Flow Subspacescited by 10
  8. 2023A Review of Predictive and Contrastive Self-supervised Learning for Medical Imagescited by 10
  9. 2022Stochastic Video Prediction with Structure and Motioncited by 8
  10. 2026Future Optical Flow Prediction Improves Robot Control & Video Generationcited by 7
  11. 2021Self-Supervision by Prediction for Object Discovery in Videoscited by 6
  12. 2021Social Processes: Self-Supervised Meta-Learning over Conversational Groups for Forecasting Nonverbal Social Cuescited by 6
  13. 2022Self-Supervised Face Presentation Attack Detection with Dynamic Grayscale Snippetscited by 5
  14. 2024Reanimating Images using Neural Representations of Dynamic Stimulicited by 5
  15. 2025ProbDiffFlow: An Efficient Learning-Free Framework for Probabilistic Single-Image Optical Flow Estimationcited by 2
  16. 2025What If : Understanding Motion Through Sparse Interactionscited by 2
  17. 2026Envisioning the Future, One Step at a Timecited by 2
  18. 2021VAE^2: Preventing Posterior Collapse of Variational Video Predictions in the Wildcited by 1
  19. 2022Wildfire Forecasting with Satellite Images and Deep Generative Modelcited by 1
  20. 2025DecoFuse: Decomposing and Fusing the "What", "Where", and "How" for Brain-Inspired fMRI-to-Video Decodingcited by 1
  21. 2025Autoregressive Flow Matching for Motion Predictioncited by 1
  22. 2021Estimating Nonplanar Flow from 2D Motion-blurred Widefield Microscopy Images via Deep Learningcited by 0
  23. 2022Stochastic Future Prediction in Real World Driving Scenarioscited by 0
  24. 2026Group-DINOmics: Incorporating People Dynamics into DINO for Self-supervised Group Activity Feature Learningcited by 0