Skip to main content
SpringerLink
Log in

Flow-Guided Transformer for Video Inpainting

  • Conference paper
  • First Online:
Computer Vision – ECCV 2022 (ECCV 2022)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 13678))

Included in the following conference series:

Abstract

We propose a flow-guided transformer, which innovatively leverage the motion discrepancy exposed by optical flows to instruct the attention retrieval in transformer for high fidelity video inpainting. More specially, we design a novel flow completion network to complete the corrupted flows by exploiting the relevant flow features in a local temporal window. With the completed flows, we propagate the content across video frames, and adopt the flow-guided transformer to synthesize the rest corrupted regions. We decouple transformers along temporal and spatial dimension, so that we can easily integrate the locally relevant completed flows to instruct spatial attention only. Furthermore, we design a flow-reweight module to precisely control the impact of completed flows on each spatial transformer. For the sake of efficiency, we introduce window partition strategy to both spatial and temporal transformers. Especially in spatial transformer, we design a dual perspective spatial MHSA, which integrates the global tokens to the window-based attention. Extensive experiments demonstrate the effectiveness of the proposed method qualitatively and quantitatively. Codes are available at https://github.com/hitachinsk/FGT.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 89.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 119.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

References

  1. Ba, J.L., Kiros, J.R., Hinton, G.E.: Layer normalization (2016)

    Google Scholar 

  2. Bertalmio, M., Bertozzi, A.L., Sapiro, G.: Navier-stokes, fluid dynamics, and image and video inpainting. In: CVPR, vol. 1, pp. 355–362 (2001)

    Google Scholar 

  3. Bhojanapalli, S., Chakrabarti, A., Glasner, D., Li, D., Unterthiner, T., Veit, A.: Understanding robustness of transformers for image classification. In: ICCV, pp. 10231–10241 (October 2021)

    Google Scholar 

  4. Caelles, S., et al.: The 2018 DAVIS challenge on video object segmentation. arXiv preprint arXiv:1803.00557 (2018)

  5. Canny, J.: A computational approach to edge detection. TPAMI PAMI 8(6), 679–698 (1986). https://doi.org/10.1109/TPAMI.1986.4767851

    Article  Google Scholar 

  6. Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 213–229. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58452-8_13

    Chapter  Google Scholar 

  7. Chang, Y.L., Liu, Z.Y., Lee, K.Y., Hsu, W.: Free-form video inpainting with 3D gated convolution and temporal PatchGAN. In: ICCV, pp. 9066–9075 (2019)

    Google Scholar 

  8. Chang, Y.L., Liu, Z.Y., Lee, K.Y., Hsu, W.: Learnable gated temporal shift module for deep video inpainting. In: BMVC (2019)

    Google Scholar 

  9. Chu, X., et al.: Twins: Revisiting the design of spatial attention in vision transformers. In: NeurIPS (2021)

    Google Scholar 

  10. Chu, X., et al.: Conditional positional encodings for vision transformers. arXiv: 2102.10882 (2021). https://arxiv.org/pdf/2102.10882.pdf

  11. Dosovitskiy, A., et al.: An image is worth 16x16 words: Transformers for image recognition at scale. In: ICLR (2021). https://openreview.net/forum?id=YicbFdNTTy

  12. Ebdelli, M., Le Meur, O., Guillemot, C.: Video inpainting with short-term windows: Application to object removal and error concealment. TIP 24(10), 3034–3047 (2015). https://doi.org/10.1109/TIP.2015.2437193

    Article  MathSciNet  MATH  Google Scholar 

  13. Fan, H., Xiong, B., Mangalam, K., Li, Y., Yan, Z., Malik, J., Feichtenhofer, C.: Multiscale vision transformers. In: ICCV, pp. 6824–6835 (October 2021)

    Google Scholar 

  14. Gao, C., Saraf, A., Huang, J.-B., Kopf, J.: Flow-edge guided video completion. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12357, pp. 713–729. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58610-2_42

    Chapter  Google Scholar 

  15. Granados, M., Tompkin, J., Kim, K., Grau, O., Kautz, J., Theobalt, C.: How not to be seen - object removal from videos of crowded scenes. Comput. Graph. Forum 31(2pt1), 219–228 (2012). https://doi.org/10.1111/j.1467-8659.2012.03000.x

  16. Granados, M., Kim, K.I., Tompkin, J., Kautz, J., Theobalt, C.: Background inpainting for videos with dynamic objects and a free-moving camera. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7572, pp. 682–695. Springer, Heidelberg (2012). https://doi.org/10.1007/978-3-642-33718-5_49

    Chapter  Google Scholar 

  17. He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770–778 (2016)

    Google Scholar 

  18. Howard, A.G., et al.: Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017)

  19. Huang, J.B., Kang, S.B., Ahuja, N., Kopf, J.: Temporally coherent completion of dynamic video. TOG 35(6), 196:1–11 (2016)

    Google Scholar 

  20. Iizuka, S., Simo-Serra, E., Ishikawa, H.: Globally and locally consistent image completion. TOG 36(4), 107:1–14 (2017)

    Google Scholar 

  21. Ke, L., Tai, Y.W., Tang, C.K.: Occlusion-aware video object inpainting. In: ICCV (2021)

    Google Scholar 

  22. Kim, D., Woo, S., Lee, J.Y., Kweon, I.S.: Deep video inpainting. In: CVPR, pp. 5792–5801 (2019)

    Google Scholar 

  23. Kingma, D.P., Ba, J.: Adam: A method for stochastic optimization. In: ICLR (2014)

    Google Scholar 

  24. Lee, S., Oh, S.W., Won, D., Kim, S.J.: Copy-and-paste networks for deep video inpainting. In: ICCV, pp. 4413–4421 (2019)

    Google Scholar 

  25. Li, A., et al.: Short-term and long-term context aggregation network for video inpainting. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12349, pp. 728–743. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58548-8_42

    Chapter  Google Scholar 

  26. Liao, L., Xiao, J., Wang, Z., Lin, C.W., Satoh, S.: Image inpainting guided by coherence priors of semantics and textures. In: CVPR, pp. 6539–6548 (June 2021)

    Google Scholar 

  27. Liu, G., Reda, F.A., Shih, K.J., Wang, T.-C., Tao, A., Catanzaro, B.: Image inpainting for irregular holes using partial convolutions. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11215, pp. 89–105. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01252-6_6

    Chapter  Google Scholar 

  28. Liu, R., et al.: Decoupled spatial-temporal transformer for video inpainting (2021)

    Google Scholar 

  29. Liu, R., et al.: Fuseformer: Fusing fine-grained information in transformers for video inpainting. In: ICCV (2021)

    Google Scholar 

  30. Liu, Z., et al.: Swin transformer: Hierarchical vision transformer using shifted windows. In: ICCV, pp. 10012–10022 (October 2021)

    Google Scholar 

  31. Matsushita, Y., Ofek, E., Ge, W., Tang, X., Shum, H.Y.: Full-frame video stabilization with motion inpainting. TPAMI 28(7), 1150–1163 (2006). https://doi.org/10.1109/TPAMI.2006.141

    Article  Google Scholar 

  32. Misra, I., Girdhar, R., Joulin, A.: An end-to-end transformer model for 3d object detection. In: ICCV, pp. 2906–2917 (Oct 2021)

    Google Scholar 

  33. Nazeri, K., Ng, E., Joseph, T., Qureshi, F., Ebrahimi, M.: Edgeconnect: Structure guided image inpainting using edge prediction. In: ICCVW (Oct 2019)

    Google Scholar 

  34. Newson, A., Almansa, A., Fradet, M., Gousseau, Y., Pérez, P.: Video inpainting of complex scenes. SIAM J. Imag. Sci. 7(4), 1993–2019 (2014)

    Article  MathSciNet  MATH  Google Scholar 

  35. Oh, S.W., Lee, S., Lee, J.Y., Kim, S.J.: Onion-peel networks for deep video completion. In: ICCV, pp. 4403–4412 (2019)

    Google Scholar 

  36. Ouyang, H., Wang, T., Chen, Q.: Internal video inpainting by implicit long-range propagation. In: ICCV (2021)

    Google Scholar 

  37. Pathak, D., Krähenbühl, P., Donahue, J., Darrell, T., Efros, A.: Context encoders: Feature learning by inpainting. In: CVPR, pp. 2536–2544 (2016)

    Google Scholar 

  38. Peng, J., Liu, D., Xu, S., Li, H.: Generating diverse structure for image inpainting with hierarchical VQ-VAE. In: CVPR, pp. 10775–10784 (2021)

    Google Scholar 

  39. Qiu, Z., Yao, T., Mei, T.: Learning spatio-temporal representation with pseudo-3d residual networks. In: ICCV, pp. 5533–5541 (2017)

    Google Scholar 

  40. Ronneberger, O., Fischer, P., Brox, T.: U-Net: Convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234–241. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-24574-4_28

    Chapter  Google Scholar 

  41. Teed, Z., Deng, J.: RAFT: Recurrent all-pairs field transforms for optical flow. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12347, pp. 402–419. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58536-5_24

    Chapter  Google Scholar 

  42. Tran, D., Bourdev, L., Fergus, R., Torresani, L., Paluri, M.: Learning spatiotemporal features with 3d convolutional networks. In: CVPR, pp. 4489–4497 (2015)

    Google Scholar 

  43. Vaswani, A., et al.: Attention is all you need. In: NeurIPS, vol. 30 (2017)

    Google Scholar 

  44. Wang, C., Huang, H., Han, X., Wang, J.: Video inpainting by jointly learning temporal structure and spatial details. In: AAAI, vol. 33, pp. 5232–5239 (2019)

    Google Scholar 

  45. Wang, H., Zhu, Y., Adam, H., Yuille, A., Chen, L.C.: Max-deeplab: End-to-end panoptic segmentation with mask transformers. In: CVPR, pp. 5463–5474 (2021)

    Google Scholar 

  46. Wang, X., et al.: Oadtr: Online action detection with transformers. In: ICCV, pp. 7565–7575 (Oct 2021)

    Google Scholar 

  47. Wang, Z., Bovik, A.C., Sheikh, H.R., Simoncelli, E.P.: Image quality assessment: From error visibility to structural similarity. TIP 13(4), 600–612 (2004)

    Google Scholar 

  48. Wu, H., et al.: Cvt: Introducing convolutions to vision transformers. In: ICCV, pp. 22–31 (Oct 2021)

    Google Scholar 

  49. Xu, N., et al.: Youtube-vos: A large-scale video object segmentation benchmark. arXiv preprint arXiv:1809.03327 (2018)

  50. Xu, R., Li, X., Zhou, B., Loy, C.C.: Deep flow-guided video inpainting. In: CVPR, pp. 3723–3732 (2019)

    Google Scholar 

  51. Xu, S., Liu, D., Xiong, Z.: E2I: Generative inpainting from edge to image. In: TCSVT (2020)

    Google Scholar 

  52. Yang, J., et al.: Focal attention for long-range interactions in vision transformers. In: NeurIPS (Dec 2021). https://www.microsoft.com/en-us/research/publication/focal-self-attention-for-local-global-interactions-in-vision-transformers/

  53. Yu, J., Lin, Z., Yang, J., Shen, X., Lu, X., Huang, T.S.: Generative image inpainting with contextual attention. In: CVPR, pp. 5505–5514 (2018)

    Google Scholar 

  54. Yu, J., Lin, Z., Yang, J., Shen, X., Lu, X., Huang, T.S.: Free-form image inpainting with gated convolution. In: ICCV, pp. 4471–4480 (2019)

    Google Scholar 

  55. Zeng, Y., Fu, J., Chao, H.: Learning joint spatial-temporal transformations for video inpainting. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12361, pp. 528–543. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58517-4_31

    Chapter  Google Scholar 

  56. Zhang, H., Mai, L., Xu, N., Wang, Z., Collomosse, J., Jin, H.: An internal learning approach to video inpainting. In: ICCV, pp. 2720–2729 (2019)

    Google Scholar 

  57. Zhang, K., Fu, J., Liu, D.: Inertia-guided flow completion and style fusion for video inpainting. In: CVPR, pp. 5982–5991 (June 2022)

    Google Scholar 

  58. Zhang, R., Isola, P., Efros, A.A., Shechtman, E., Wang, O.: The unreasonable effectiveness of deep features as a perceptual metric. In: CVPR, pp. 586–595 (2018)

    Google Scholar 

  59. Zou, X., Yang, L., Liu, D., Lee, Y.J.: Progressive temporal feature alignment network for video inpainting. In: CVPR (2021)

    Google Scholar 

Download references

Acknowledgment

This work was supported by the Natural Science Foundation of China under Grants 62036005, 62022075, and 62021001, and by the Fundamental Research Funds for the Central Universities under Contract No. WK3490000006.

Author information

Authors and Affiliations

  1. University of Science and Technology of China, Hefei, China

    Kaidong Zhang & Dong Liu

  2. Microsoft Research Asia, Beijing, China

    Jingjing Fu

Authors
  1. Kaidong Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Jingjing Fu
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Dong Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Jingjing Fu .

Editor information

Editors and Affiliations

  1. Tel Aviv University, Tel Aviv, Israel

    Shai Avidan

  2. University College London, London, UK

    Gabriel Brostow

  3. Google AI, Accra, Ghana

    Moustapha Cissé

  4. University of Catania, Catania, Italy

    Giovanni Maria Farinella

  5. Facebook (United States), Menlo Park, CA, USA

    Tal Hassner

1 Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary material 1 (pdf 6252 KB)

Rights and permissions

Reprints and permissions

Copyright information

© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Zhang, K., Fu, J., Liu, D. (2022). Flow-Guided Transformer for Video Inpainting. In: Avidan, S., Brostow, G., Cissé, M., Farinella, G.M., Hassner, T. (eds) Computer Vision – ECCV 2022. ECCV 2022. Lecture Notes in Computer Science, vol 13678. Springer, Cham. https://doi.org/10.1007/978-3-031-19797-0_5

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-19797-0_5

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-19796-3

  • Online ISBN: 978-3-031-19797-0

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation