mlsanityData to 14 Oct 2026

Free-form Video Inpainting with 3D Gated Convolution and Temporal PatchGAN

arXiv 1904.10247 ↗First posted 23 Apr 2019cs.CVcited by 87

Not on the map. Why?

Abstract (arXiv)

Free-form video inpainting is a very challenging task that could be widely used for video editing such as text removal. Existing patch-based methods could not handle non-repetitive structures such as faces, while directly applying image-based inpainting models to videos will result in temporal inconsistency (see http://bit.ly/2Fu1n6b ). In this paper, we introduce a deep learn-ing based free-form video inpainting model, with proposed 3D gated convolutions to tackle the uncertainty of free-form masks and a novel Temporal PatchGAN loss to enhance temporal consistency. In addition, we collect videos and design a free-form mask generation algorithm to build the free-form video inpainting (FVI) dataset for training and evaluation of video inpainting models. We demonstrate the benefits of these components and experiments on both the FaceForensics and our FVI dataset suggest that our method is superior to existing ones. Related source code, full-resolution result videos and the FVI dataset could be found on Github https://github.com/amjltc295/Free-Form-Video-Inpainting .

Key facts. Cited by 87 papers in the map (data through 14 Oct 2026). First posted on arXiv 23 Apr 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 15; 2022: 13; 2023: 15; 2024: 17; 2025: 15; 2026: 12.

87 papers.

Sort:

By area:

  1. 2023ProPainter: Improving Propagation and Transformer for Video Inpaintingcited by 197
  2. 2022Towards An End-to-End Framework for Flow-Guided Video Inpaintingcited by 113
  3. 2021FuseFormer: Fusing Fine-Grained Information in Transformers for Video Inpaintingcited by 95
  4. 2025VideoPainter: Any-length Video Inpainting and Editing with Plug-and-Play Context Controlcited by 84
  5. 2022Flow-Guided Transformer for Video Inpaintingcited by 59
  6. 2024Deep Learning-based Image and Video Inpainting: A Surveycited by 44
  7. 2024Generative Omnimatte: Learning to Decompose Video into Layerscited by 38
  8. 2025ROSE: Remove Objects with Side Effects in Videoscited by 38
  9. 2021Progressive Temporal Feature Alignment Network for Video Inpaintingcited by 35
  10. 2024Towards Language-Driven Video Inpainting via Multimodal Large Language Modelscited by 33
  11. 2021Dense Deep Unfolding Network with 3D-CNN Prior for Snapshot Compressive Imagingcited by 31
  12. 2022Bringing Old Films Back to Lifecited by 31
38 more
  1. 2021Occlusion-Aware Video Object Inpaintingcited by 30
  2. 2021Decoupled Spatial-Temporal Transformer for Video Inpaintingcited by 28
  3. 2022ClothFormer:Taming Video Virtual Try-on in All Modulecited by 26
  4. 2022Video Demoireing with Relation-Based Temporal Consistencycited by 24
  5. 2021High-resolution Depth Maps Imaging via Attention-based Hierarchical Multi-modal Fusioncited by 20
  6. 2022Error Compensation Framework for Flow-Guided Video Inpaintingcited by 20
  7. 2021Internal Video Inpainting by Implicit Long-range Propagationcited by 19
  8. 2023EfficientSCI: Densely Connected Network with Space-time Factorization for Large-scale Video Snapshot Compressive Imagingcited by 18
  9. 2021Free-form tumor synthesis in computed tomography images via richer generative adversarial networkcited by 16
  10. 2025OmnimatteZero: Fast Training-free Omnimatte with Pre-trained Video Diffusion Modelscited by 16
  11. 2026NTIRE 2026 Challenge on Bitstream-Corrupted Video Restoration: Methods and Resultscited by 16
  12. 2023Bitstream-Corrupted Video Recovery: A Novel Benchmark Dataset and Methodcited by 15
  13. 2026EffectErase: Joint Video Object Removal and Insertion for High-Quality Effect Erasingcited by 15
  14. 2021The DEVIL is in the Details: A Diagnostic Evaluation Benchmark for Video Inpaintingcited by 12
  15. 2021Flow-Guided Video Inpainting with Scene Templatescited by 12
  16. 2021Deep Video Inpainting Detectioncited by 11
  17. 2026PISCO: Precise Video Instance Insertion with Sparse Controlcited by 10
  18. 2021Let's See Clearly: Contaminant Artifact Removal for Moving Camerascited by 9
  19. 2023GRACE: Loss-Resilient Real-Time Video through Neural Codecscited by 9
  20. 2022Semi-Supervised Video Inpainting with Cycle Consistency Constraintscited by 8
  21. 2021Deep Face Video Inpainting via UV Mappingcited by 7
  22. 2022Feature-Aligned Video Raindrop Removal with Temporal Constraintscited by 7
  23. 2024MambaSCI: Efficient Mamba-UNet for Quad-Bayer Patterned Video Snapshot Compressive Imagingcited by 7
  24. 2021A Review on Visual Privacy Preservation Techniques for Active and Assisted Livingcited by 6
  25. 2023Exploiting Optical Flow Guidance for Transformer-Based Video Inpaintingcited by 6
  26. 2026Object-WIPER : Training-Free Object and Associated Effect Removal in Videoscited by 6
  27. 2022Beyond the Field-of-View: Enhancing Scene Visibility and Perception with Clip-Recurrent Transformercited by 5
  28. 2023Deficiency-Aware Masked Transformer for Video Inpaintingcited by 5
  29. 2022Paying U-Attention to Textures: Multi-Stage Hourglass Vision Transformer for Universal Texture Synthesiscited by 4
  30. 2023Exemplar-based Video Colorization with Long-term Spatiotemporal Dependencycited by 4
  31. 2025BVINet: Unlocking Blind Video Inpainting with Zero Annotationscited by 4
  32. 2025OutDreamer: Video Outpainting with a Diffusion Transformercited by 4
  33. 2023You Can Mask More For Extremely Low-Bitrate Image Compressioncited by 3
  34. 2023A Lightweight Transformer for Faster and Robust EBSD Data Collectioncited by 3
  35. 2023How to train your VAEcited by 3
  36. 2023DeepDR: Deep Structure-Aware RGB-D Inpainting for Diminished Realitycited by 3
  37. 2024Towards Online Real-Time Memory-based Video Inpainting Transformerscited by 3
  38. 2024Laplacian-guided Entropy Model in Neural Codec with Blur-dissipated Synthesiscited by 3

50 most cited of 87 All 87 (JSON)