mlsanityData to 14 Oct 2026

FILM: Frame Interpolation for Large Motion

arXiv 2202.04901 ↗First posted 10 Feb 2022cs.CVcited by 153

Not on the map. Why?

Cited by 40 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We present a frame interpolation algorithm that synthesizes multiple intermediate frames from two input images with large in-between motion. Recent methods use multiple networks to estimate optical flow or depth and a separate network dedicated to frame synthesis. This is often complex and requires scarce optical flow or depth ground-truth. In this work, we present a single unified network, distinguished by a multi-scale feature extractor that shares weights at all scales, and is trainable from frames alone. To synthesize crisp and pleasing frames, we propose to optimize our network with the Gram matrix loss that measures the correlation difference between feature maps. Our approach outperforms state-of-the-art methods on the Xiph large motion benchmark. We also achieve higher scores on Vimeo-90K, Middlebury and UCF101, when comparing to methods that use perceptual losses. We study the effect of weight sharing and of training with datasets of increasing motion range. Finally, we demonstrate our model's effectiveness in synthesizing high quality and temporally coherent videos on a challenging near-duplicate photos dataset. Codes and pre-trained models are available at https://film-net.github.io.

Key facts. Cited by 153 papers in the map (data through 14 Oct 2026). Builds on 30 of its 43 references that are in the map. First posted on arXiv 10 Feb 2022.

Builds on

30 of 43 references.

References · 30

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  3. 2021Alias-Free Generative Adversarial Networkscited by 1,184
  4. 2017PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volumecited by 968
  5. 2017Video Enhancement with Task-Oriented Flowcited by 619
  6. 2015Holistically-Nested Edge Detectioncited by 592
  7. 2017The Perception-Distortion Tradeoffcited by 587
  8. 2018Image Inpainting for Irregular Holes Using Partial Convolutionscited by 505
  9. 2017Super SloMo: High Quality Estimation of Multiple Intermediate Frames for Video Interpolationcited by 326
  10. 2020Softmax Splatting for Video Frame Interpolationcited by 279
  11. 2019Depth-Aware Video Frame Interpolationcited by 234
  12. 2016Generating Images with Perceptual Similarity Metrics based on Deep Networkscited by 222
18 more
  1. 2017Video Frame Interpolation via Adaptive Separable Convolutioncited by 213
  2. 2017Video Frame Synthesis using Deep Voxel Flowcited by 209
  3. 2016EnhanceNet: Single Image Super-Resolution Through Automated Texture Synthesiscited by 178
  4. 2017Video Frame Interpolation via Adaptive Convolutioncited by 158
  5. 2018Context-aware Synthesis for Video Frame Interpolationcited by 153
  6. 2019AdaCoF: Adaptive Collaboration of Flows for Video Frame Interpolationcited by 134
  7. 2019Iterative Residual Refinement for Joint Optical Flow and Occlusion Estimationcited by 131
  8. 2021XVFI: eXtreme Video Frame Interpolationcited by 126
  9. 2020BMBC:Bilateral Motion Estimation with Bilateral Cost Volume for Video Interpolationcited by 118
  10. 2021Asymmetric Bilateral Motion Estimation for Video Frame Interpolationcited by 101
  11. 2020Zooming Slow-Mo: Fast and Accurate One-Stage Space-Time Video Super-Resolutioncited by 91
  12. 2021CDFI: Compression-Driven Network Design for Frame Interpolationcited by 56
  13. 2018SDCNet: Video Prediction Using Spatially-Displaced Convolutioncited by 50
  14. 2019Unsupervised Video Interpolation Using Cycle Consistencycited by 44
  15. 2019SENSE: a Shared Encoder Network for Scene-flow Estimationcited by 38
  16. 2018Learning to Synthesize Motion Blurcited by 37
  17. 2020Revisiting Adaptive Convolutions for Video Frame Interpolationcited by 32
  18. 2017Frame Interpolation with Multi-Scale Deep Loss Functions and Generative Adversarial Networkscited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 13; 2023: 29; 2024: 44; 2025: 35; 2026: 32.

153 papers.

Sort:

By area:

  1. 2022Make-A-Video: Text-to-Video Generation without Text-Video Datacited by 1,742
  2. 2023AMT: All-Pairs Multi-Field Transforms for Efficient Frame Interpolationcited by 180
  3. 2023DreamPose: Fashion Image-to-Video Synthesis via Stable Diffusioncited by 167
  4. 2025Difix3D+: Improving 3D Reconstructions with Single-Step Diffusion Modelscited by 161
  5. 2023TryOnDiffusion: A Tale of Two UNetscited by 141
  6. 2023Consistent View Synthesis with Pose-Guided Diffusion Modelscited by 117
  7. 2023Extracting Motion and Appearance via Inter-Frame Attention for Efficient Video Frame Interpolationcited by 98
  8. 2023LDMVFI: Video Frame Interpolation with Latent Diffusion Modelscited by 89
  9. 2023VideoGen: A Reference-Guided Latent Diffusion Approach for High Definition Text-to-Video Generationcited by 74
  10. 2024Video Interpolation with Diffusion Modelscited by 68
  11. 2024ToonCrafter: Generative Cartoon Interpolationcited by 68
  12. 2024Controlling Space and Time with Diffusion Modelscited by 66
38 more
  1. 2023Shape-aware Text-driven Layered Video Editingcited by 54
  2. 2022DiffDreamer: Towards Consistent Unsupervised Single-view Scene Extrapolation with Conditional Diffusion Modelscited by 51
  3. 2024MarDini: Masked Autoregressive Diffusion for Video Generation at Scalecited by 49
  4. 2024Generative Inbetweening: Adapting Image-to-Video Models for Keyframe Interpolationcited by 44
  5. 2023Towards Scalable Neural Representation for Diverse Videoscited by 37
  6. 2022Tell Me What Happened: Unifying Text-guided Video Completion via Multimodal Masked Video Generationcited by 32
  7. 2024TANGO: Co-Speech Gesture Video Reenactment with Hierarchical Audio Motion Embedding and Diffusion Interpolationcited by 32
  8. 2024Sparse Global Matching for Video Frame Interpolation with Large Motioncited by 28
  9. 2023Mask Propagation for Efficient Video Semantic Segmentationcited by 26
  10. 2024Framer: Interactive Frame Interpolationcited by 24
  11. 2024Generative Inbetweening through Frame-wise Conditions-Driven Video Generationcited by 24
  12. 2023BiFormer: Learning Bilateral Motion Estimation via Bilateral Transformer for 4K Video Frame Interpolationcited by 23
  13. 2024Event-assisted Low-Light Video Object Segmentationcited by 22
  14. 2024VFIMamba: Video Frame Interpolation with State Space Modelscited by 22
  15. 2024Explorative Inbetweening of Time and Spacecited by 21
  16. 2024VividDream: Generating 3D Scene with Ambient Dynamicscited by 21
  17. 2024VASE: Object-Centric Appearance and Shape Manipulation of Real Videoscited by 20
  18. 2025Sharp Monocular View Synthesis in Less Than a Secondcited by 20
  19. 2025EDEN: Enhanced Diffusion for High-quality Large-motion Video Frame Interpolationcited by 19
  20. 2025R3D2: Realistic 3D Asset Insertion via Diffusion for Autonomous Driving Simulationcited by 18
  21. 2024AniClipart: Clipart Animation with Text-to-Video Priorscited by 17
  22. 2023Implicit Event-RGBD Neural SLAMcited by 16
  23. 2024Generalizable Implicit Motion Modeling for Video Frame Interpolationcited by 16
  24. 2024DreamMover: Leveraging the Prior of Diffusion Models for Image Interpolation with Large Motioncited by 16
  25. 2023Bitstream-Corrupted Video Recovery: A Novel Benchmark Dataset and Methodcited by 15
  26. 2023Event-based Continuous Color Video Decompression from Single Framescited by 15
  27. 2024CycleINR: Cycle Implicit Neural Representation for Arbitrary-Scale Volumetric Super-Resolution of Medical Datacited by 15
  28. 2024OnlyFlow: Optical Flow based Motion Conditioning for Video Diffusion Modelscited by 15
  29. 2024Invisible Reflections: Leveraging Infrared Laser Reflections to Target Traffic Sign Perceptioncited by 14
  30. 2023SportsSloMo: A New Benchmark and Baselines for Human-centric Video Frame Interpolationcited by 11
  31. 2023MaskINT: Video Editing via Interpolative Non-autoregressive Masked Transformerscited by 11
  32. 2024LAVIB: A Large-scale Video Interpolation Benchmarkcited by 11
  33. 2024Disentangled Motion Modeling for Video Frame Interpolationcited by 11
  34. 2024IDOL: Unified Dual-Modal Latent Diffusion for Human-Centric Joint Video-Depth Generationcited by 11
  35. 2026Generative World Renderercited by 10
  36. 2023Deep Geometrized Cartoon Line Inbetweeningcited by 9
  37. 2024ETAP: Event-based Tracking of Any Pointcited by 9
  38. 2025BF-STVSR: B-Splines and Fourier-Best Friends for High Fidelity Spatial-Temporal Video Super-Resolutioncited by 9

50 most cited of 153 All 153 (JSON)