mlsanityData to 7 Oct 2026

Deep Flow-Guided Video Inpainting

arXiv 1905.02884 ↗First posted 8 May 2019cs.CVcited by 116

Not on the map. Why?

Abstract (arXiv)

Video inpainting, which aims at filling in missing regions of a video, remains challenging due to the difficulty of preserving the precise spatial and temporal coherence of video contents. In this work we propose a novel flow-guided video inpainting approach. Rather than filling in the RGB pixels of each frame directly, we consider video inpainting as a pixel propagation problem. We first synthesize a spatially and temporally coherent optical flow field across video frames using a newly designed Deep Flow Completion network. Then the synthesized flow field is used to guide the propagation of pixels to fill up the missing regions in the video. Specifically, the Deep Flow Completion network follows a coarse-to-fine refinement to complete the flow fields, while their quality is further improved by hard flow example mining. Following the guide of the completed flow, the missing video regions can be filled up precisely. Our method is evaluated on DAVIS and YouTube-VOS datasets qualitatively and quantitatively, achieving the state-of-the-art performance in terms of inpainting quality and speed.

Key facts. Cited by 116 papers in the map (data through 7 Oct 2026). First posted on arXiv 8 May 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 22; 2022: 20; 2023: 21; 2024: 14; 2025: 21; 2026: 18.

116 papers.

Sort:

By area:

  1. 2022FlowFormer: A Transformer Architecture for Optical Flowcited by 273
  2. 2023ProPainter: Improving Propagation and Transformer for Video Inpaintingcited by 193
  3. 2024SEA-RAFT: Simple, Efficient, Accurate RAFT for Optical Flowcited by 169
  4. 2023FlowFormer++: Masked Cost Volume Autoencoding for Pretraining Optical Flow Estimationcited by 114
  5. 2022Towards An End-to-End Framework for Flow-Guided Video Inpaintingcited by 111
  6. 2021FuseFormer: Fusing Fine-Grained Information in Transformers for Video Inpaintingcited by 94
  7. 2025VideoPainter: Any-length Video Inpainting and Editing with Plug-and-Play Context Controlcited by 83
  8. 2023VideoFlow: Exploiting Temporal Cues for Multi-frame Optical Flow Estimationcited by 82
  9. 2023AVID: Any-Length Video Inpainting with Diffusion Modelcited by 81
  10. 2022Removing Objects From Neural Radiance Fieldscited by 66
  11. 2022High-fidelity 3D GAN Inversion by Pseudo-multi-view Optimizationcited by 65
  12. 2022Flow-Guided Transformer for Video Inpaintingcited by 59
38 more
  1. 2024InFusion: Inpainting 3D Gaussians via Learning Depth Completion from Diffusion Priorcited by 55
  2. 2021TransFill: Reference-guided Image Inpainting by Merging Multiple Color and Spatial Transformationscited by 48
  3. 2024Deep Learning-based Image and Video Inpainting: A Surveycited by 44
  4. 2023DNeRV: Modeling Inherent Dynamics via Difference Neural Representation for Videoscited by 42
  5. 2021Progressive Temporal Feature Alignment Network for Video Inpaintingcited by 34
  6. 2022Learning Optical Flow with Adaptive Graph Reasoningcited by 33
  7. 2022Tell Me What Happened: Unifying Text-guided Video Completion via Multimodal Masked Video Generationcited by 32
  8. 2022Bringing Old Films Back to Lifecited by 31
  9. 2021Occlusion-Aware Video Object Inpaintingcited by 30
  10. 2021Decoupled Spatial-Temporal Transformer for Video Inpaintingcited by 28
  11. 2022ClothFormer:Taming Video Virtual Try-on in All Modulecited by 26
  12. 2023Learning Optical Flow from Event Camera with Rendered Datasetcited by 26
  13. 2021Learning Semantic-Aware Dynamics for Video Predictioncited by 21
  14. 2023Look Ma, No Hands! Agent-Environment Factorization of Egocentric Videoscited by 21
  15. 2022Error Compensation Framework for Flow-Guided Video Inpaintingcited by 20
  16. 2021Internal Video Inpainting by Implicit Long-range Propagationcited by 19
  17. 2026NTIRE 2026 Challenge on Bitstream-Corrupted Video Restoration: Methods and Resultscited by 15
  18. 2023Bitstream-Corrupted Video Recovery: A Novel Benchmark Dataset and Methodcited by 14
  19. 2025MTV-Inpaint: Multi-Task Long Video Inpaintingcited by 14
  20. 2021Seeing Through Clouds in Satellite Imagescited by 13
  21. 2022BiSTNet: Semantic Image Prior Guided Bidirectional Temporal Feature Fusion for Deep Exemplar-based Video Colorizationcited by 13
  22. 2024UniPaint: Unified Space-time Video Inpainting via Mixture-of-Expertscited by 13
  23. 2021Flow-Guided Video Inpainting with Scene Templatescited by 12
  24. 2022Fast-Vid2Vid: Spatial-Temporal Compression for Video-to-Video Synthesiscited by 12
  25. 2022DeViT: Deformed Vision Transformers in Video Inpaintingcited by 12
  26. 2021Deep Video Inpainting Detectioncited by 11
  27. 2021The DEVIL is in the Details: A Diagnostic Evaluation Benchmark for Video Inpaintingcited by 11
  28. 2023Flow-Guided Diffusion for Video Inpaintingcited by 11
  29. 2025TACO: Taming Diffusion for in-the-wild Video Amodal Completioncited by 10
  30. 2021Let's See Clearly: Contaminant Artifact Removal for Moving Camerascited by 9
  31. 2024Infrared Small Target Detection in Satellite Videos: A New Dataset and A Novel Recurrent Feature Refinement Frameworkcited by 9
  32. 2026PISCO: Precise Video Instance Insertion with Sparse Controlcited by 9
  33. 2021A Shape-Aware Retargeting Approach to Transfer Human Motion and Appearance in Monocular Videoscited by 8
  34. 2021M3L: Language-based Video Editing via Multi-Modal Multi-Level Transformerscited by 8
  35. 2022Semi-Supervised Video Inpainting with Cycle Consistency Constraintscited by 8
  36. 2023Event-Free Moving Object Segmentation from Moving Ego Vehiclecited by 8
  37. 2024Semantically Consistent Video Inpainting with Conditional Diffusion Modelscited by 8
  38. 2021Deep Face Video Inpainting via UV Mappingcited by 7

50 most cited of 116 All 116 (JSON)