mlsanityData to 7 Oct 2026

Fr'echet Video Motion Distance: A Metric for Evaluating Motion Consistency in Videos

arXiv 2407.16124 ↗First posted 23 Jul 2024cs.CVcited by 54

Not on the map. Why?

Abstract (arXiv)

Significant advancements have been made in video generative models recently. Unlike image generation, video generation presents greater challenges, requiring not only generating high-quality frames but also ensuring temporal consistency across these frames. Despite the impressive progress, research on metrics for evaluating the quality of generated videos, especially concerning temporal and motion consistency, remains underexplored. To bridge this research gap, we propose Fr'echet Video Motion Distance (FVMD) metric, which focuses on evaluating motion consistency in video generation. Specifically, we design explicit motion features based on key point tracking, and then measure the similarity between these features via the Fr'echet distance. We conduct sensitivity analysis by injecting noise into real videos to verify the effectiveness of FVMD. Further, we carry out a large-scale human study, demonstrating that our metric effectively detects temporal noise and aligns better with human perceptions of generated video quality than existing metrics. Additionally, our motion features can consistently improve the performance of Video Quality Assessment (VQA) models, indicating that our approach is also applicable to unary video quality evaluation. Code is available at https://github.com/ljh0v0/FMD-frechet-motion-distance.

Key facts. Cited by 54 papers in the map (data through 7 Oct 2026). Builds on 41 of its 51 references that are in the map. First posted on arXiv 23 Jul 2024.

Builds on

41 of 51 references.

References · 41

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  4. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,466
  5. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  6. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
  7. 2017Quo Vadis, Action Recognition? A New Model and the Kinetics Datasetcited by 3,259
  8. 2022Video Diffusion Modelscited by 2,280
  9. 2022Imagen Video: High Definition Video Generation with Diffusion Modelscited by 1,765
  10. 2023VBench: Comprehensive Benchmark Suite for Video Generative Modelscited by 1,755
  11. 2022Make-A-Video: Text-to-Video Generation without Text-Video Datacited by 1,725
  12. 2018Towards Accurate Generative Models of Video: A New Metric & Challengescited by 1,204
29 more
  1. 2022CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformerscited by 973
  2. 2023Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animationcited by 683
  3. 2021VideoGPT: Video Generation using VQ-VAE and Transformerscited by 651
  4. 2022Phenaki: Variable Length Video Generation From Open Domain Textual Descriptioncited by 475
  5. 2022Latent Video Diffusion Models for High-Fidelity Long Video Generationcited by 385
  6. 2016Generating Videos with Scene Dynamicscited by 376
  7. 2023MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Modelcited by 330
  8. 2022MCVD: Masked Conditional Video Diffusion for Prediction, Generation, and Interpolationcited by 307
  9. 2021StyleGAN-V: A Continuous Video Generator with the Price, Image Quality and Perks of StyleGAN2cited by 300
  10. 2023PointOdyssey: A Large-Scale Synthetic Dataset for Long-Term Point Trackingcited by 274
  11. 2021N"UWA: Visual Synthesis Pre-training for Neural visUal World creAtioncited by 253
  12. 2018Stochastic Video Generation with a Learned Priorcited by 244
  13. 2022Long Video Generation with Time-Agnostic VQGAN and Time-Sensitive Transformercited by 244
  14. 2017Stochastic Variational Video Predictioncited by 234
  15. 2016Temporal Generative Adversarial Nets with Singular Value Clippingcited by 198
  16. 2019Few-shot Video-to-Video Synthesiscited by 196
  17. 2022FAST-VQA: Efficient End-to-end Video Quality Assessment with Fragment Samplingcited by 179
  18. 2018Stochastic Adversarial Video Predictioncited by 173
  19. 2019Quality Assessment of In-the-Wild Videoscited by 164
  20. 2017Self-Supervised Visual Planning with Temporal Skip Connectionscited by 137
  21. 2022A Deep Learning based No-reference Quality Assessment Model for UGC Videoscited by 128
  22. 2018Train Sparsely, Generate Densely: Memory-efficient Unsupervised Training of High-resolution Temporal GANcited by 120
  23. 2020Stochastic Latent Residual Video Predictioncited by 106
  24. 2019Improved Conditional VRNNs for Video Predictioncited by 104
  25. 2021Stochastic Image-to-Video Synthesis using cINNscited by 49
  26. 2021iPOKE: Poking a Still Image for Controlled Stochastic Video Synthesiscited by 42
  27. 2024Video Diffusion Models: A Surveycited by 28
  28. 2024NTIRE 2024 Quality Assessment of AI-Generated Content Challengecited by 20
  29. 2021Self-supervised 3D Representation Learning of Dressed Humans from Social Media Videoscited by 12

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 5; 2025: 22; 2026: 27.

54 papers.

Sort:

By area:

  1. 2025GAIA-2: A Controllable Multi-View Generative World Model for Autonomous Drivingcited by 178
  2. 2024VideoDPO: Omni-Preference Alignment for Video Diffusion Generationcited by 102
  3. 20253D Scene Generation: A Surveycited by 24
  4. 2024Generative Inbetweening through Frame-wise Conditions-Driven Video Generationcited by 23
  5. 2025Simulating the Real World: A Unified Survey of Multimodal Generative Modelscited by 14
  6. 2026Physion-Eval: Evaluating Physical Realism in Generated Video via Human Reasoningcited by 13
  7. 2025DanceTogether! Identity-Preserving Multi-Person Interactive Video Generationcited by 12
  8. 2025Video Unlearning via Low-Rank Refusal Vectorcited by 11
  9. 2025Direct Motion Models for Assessing Generated Videoscited by 10
  10. 2025Model Already Knows the Best Noise: Bayesian Active Noise Selection via Attention in Video Diffusion Modelcited by 10
  11. 2025What Happens Next? Anticipating Future Motion by Generating Point Trajectoriescited by 9
  12. 2025ImagerySearch: Adaptive Test-Time Search for Video Generation Beyond Semantic Dependency Constraintscited by 9
38 more
  1. 2025AceVFI: A Comprehensive Survey of Advances in Video Frame Interpolationcited by 8
  2. 2025Generative Artificial Intelligence in Medical Imaging: Foundations, Progress, and Clinical Translationcited by 8
  3. 2026VQQA: An Agentic Approach for Video Evaluation and Quality Improvementcited by 8
  4. 2024Video Is Worth a Thousand Images: Exploring the Latest Trends in Long Video Generationcited by 7
  5. 2025Benchmarking Scientific Understanding and Reasoning for Video Generation using VideoScience-Benchcited by 6
  6. 2026Physics-IQ Verifiedcited by 6
  7. 2025Unveiling Audio Deepfake Origins: A Deep Metric learning And Conformer Network Approach With Ensemble Fusioncited by 5
  8. 2025ContextAnyone: Context-Aware Diffusion for Character-Consistent Text-to-Video Generationcited by 5
  9. 2026PhyCo: Learning Controllable Physical Priors for Generative Motioncited by 5
  10. 2024Speech2rtMRI: Speech-Guided Diffusion Model for Real-time MRI Video of the Vocal Tract during Speechcited by 4
  11. 2025DLFR-VAE: Dynamic Latent Frame Rate VAE for Video Generationcited by 4
  12. 2026Forecasting Motion in the Wildcited by 4
  13. 2026Motion Forcing: A Decoupled Framework for Robust Video Generation in Motion Dynamicscited by 3
  14. 2026World Models: A Comprehensive Survey of Architectures, Methodologies, Reasoning Paradigms, and Applicationscited by 3
  15. 2026Learning Explicit Physical Parameter Control and Benchmarking for Video Generationcited by 3
  16. 2025Learning Zero-Shot Subject-Driven Video Generation Using 1% Computecited by 2
  17. 2025LVTINO: LAtent Video consisTency INverse sOlver for High Definition Video Restorationcited by 2
  18. 2025Learning to Generate Rigid Body Interactions with Video Diffusion Modelscited by 2
  19. 2025Low-Bitrate Video Compression through Semantic-Conditioned Diffusioncited by 2
  20. 2026HumanScore: Benchmarking Human Motions in Generated Videoscited by 2
  21. 2026GEOPHYS: The Geometry of Physical Plausibilitycited by 2
  22. 2025DynaMind: Reconstructing Dynamic Visual Scenes from EEG by Aligning Temporal Dynamics and Multimodal Semantics to Guided Diffusioncited by 1
  23. 2026MorphGS: Morphology-Adaptive Articulated 3D Motion Transfer from Videoscited by 1
  24. 2026GT-SVJ: Generative-Transformer-Based Self-Supervised Video Judge For Efficient Video Reward Modelingcited by 1
  25. 2026FrameDiT: Diffusion Transformer with Matrix Attention for Efficient Video Generationcited by 1
  26. 2026Measuring 3D Spatial Geometric Consistency in Dynamic Video Generationcited by 1
  27. 2026Auditing Generalization in AI-Generated Video Detection: A Six-Control Protocol and the VidAudit Toolkitcited by 1
  28. 2026CaliBench: Are the Stochastic Dynamics of Video World Models Physically Calibrated?cited by 1
  29. 2026BeyondMasks: Evaluating Causal and Physical Consistency in Video Object Removalcited by 1
  30. 2024Motion Dreamer: Boundary Conditional Motion Reasoning for Physically Coherent Video Generationcited by 0
  31. 2025Efficient motion-based metrics for video frame interpolationcited by 0
  32. 2025LiDAR-BIND-T: Improved and Temporally Consistent Sensor Modality Translation and Fusion for Robotic Applicationscited by 0
  33. 2026EmbedTalk: Talking Head Synthesis using Gaussian Embeddingscited by 0
  34. 2026Steering Video Diffusion Transformers with Massive Activationscited by 0
  35. 2026TrajLoom: Dense Future Trajectory Generation from Videocited by 0
  36. 2026HuM-Eval: A Coarse-to-Fine Framework for Human-Centric Video Evaluationcited by 0
  37. 2026Generative Relightable Avatarscited by 0
  38. 2026Inference-Time Concept Suppression and Video-Centric Evaluation for Text-to-Video Modelscited by 0

50 most cited of 54 All 54 (JSON)