Skip to main content

Deep Bayesian Video Frame Interpolation

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

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 13675))

Included in the following conference series:

Abstract

We present deep Bayesian video frame interpolation, a novel approach for upsampling a low frame-rate video temporally to its higher frame-rate counterpart. Our approach learns posterior distributions of optical flows and frames to be interpolated, which is optimized via learned gradient descent for fast convergence. Each learned step is a lightweight network manipulating gradients of the log-likelihood of estimated frames and flows. Such gradients, parameterized either explicitly or implicitly, model the fidelity of current estimations when matching real image and flow distributions to explain the input observations. With this approach we show new records on 8 of 10 benchmarks, using an architecture with half the parameters of the state-of-the-art model. Code and models are publicly available at https://github.com/Oceanlib/DBVI.

Z. Yu and X. Xiang - The work is done during an internship at SenseTime Research and Tetras. AI.

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

Access this chapter

Subscribe and save

Springer+ Basic
EUR 32.99 /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

Notes

  1. 1.

    Please refer to the supplementary material for more discussions on implementation.

  2. 2.

    In the supplementary material we provide a more detailed description.

References

  1. Adler, J., Öktem, O.: Solving ill-posed inverse problems using iterative deep neural networks. Inverse Prob. 33(12), 124007 (2017)

    Google Scholar 

  2. Adler, J., Öktem, O.: Learned primal-dual reconstruction. IEEE Trans. Med. Imag. (TMI) 37(6), 1322–1332 (2018)

    Article  Google Scholar 

  3. Bao, W., Lai, W.S., Ma, C., Zhang, X., Gao, Z., Yang, M.H.: Depth-aware video frame interpolation. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3703–3712 (2019)

    Google Scholar 

  4. Bao, W., Lai, W.S., Zhang, X., Gao, Z., Yang, M.H.: Memc-net: motion estimation and motion compensation driven neural network for video interpolation and enhancement. IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI) 43(3), 933–948 (2019)

    Article  Google Scholar 

  5. Cheng, X., Chen, Z.: Multiple video frame interpolation via enhanced deformable separable convolution. In: IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) (2021)

    Google Scholar 

  6. Chi, Z., Nasiri, R.M., Liu, Z., Lu, J., Tang, J., Plataniotis, K.N.: All at once: temporally adaptive multi-frame interpolation with advanced motion modeling. In: European Conference on Computer Vision (ECCV), vol. 12372, pp. 107–123 (2020)

    Google Scholar 

  7. Choi, M., Kim, H., Han, B., Xu, N., Lee, K.M.: Channel attention is all you need for video frame interpolation. In: AAAI Conference on Artificial Intelligence (AAAI), pp. 10663–10671 (2020)

    Google Scholar 

  8. Dosovitskiy, A., et al.: Flownet: learning optical flow with convolutional networks. In: IEEE International Conference on Computer Vision (ICCV), pp. 2758–2766 (2015)

    Google Scholar 

  9. Flynn, J., et al.: Deepview: view synthesis with learned gradient descent. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2367–2376 (2019)

    Google Scholar 

  10. Gui, S., Wang, C., Chen, Q., Tao, D.: Featureflow: robust video interpolation via structure-to-texture generation. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 14004–14013 (2020)

    Google Scholar 

  11. Gupta, A., Aich, A., Roy-Chowdhury, A.K.: Alanet: adaptive latent attention network for joint video deblurring and interpolation. In: ACM International Conference on Multimedia (ACMMM), pp. 256–264 (2020)

    Google Scholar 

  12. Hendrycks, D., Gimpel, K.: Gaussian error linear units (gelus). Arxiv preprint, 1606.08415 [cs.CV] (2016)

    Google Scholar 

  13. Huang, G., Liu, Z., Van Der Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4700–4708 (2017)

    Google Scholar 

  14. Jaderberg, M., Simonyan, K., Zisserman, A., Kavukcuoglu, K.: Spatial transformer networks. In: Advances in Neural Information Processing Systems (NeurIPS), pp. 2017–2025 (2015)

    Google Scholar 

  15. Jiang, H., Sun, D., Jampani, V., Yang, M., Learned-Miller, E.G., Kautz, J.: Super slomo: high quality estimation of multiple intermediate frames for video interpolation. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 9000–9008 (2018)

    Google Scholar 

  16. Kalluri, T., Pathak, D., Chandraker, M., Tran, D.: Flavr: flow-agnostic video representations for fast frame interpolation. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2021)

    Google Scholar 

  17. Kingma, D.P., Dhariwal, P.: Glow: generative flow with invertible 1 \(\times \) 1 convolutions. In: Advances in Neural Information Processing Systems (NeurIPS), pp. 10236–10245 (2018)

    Google Scholar 

  18. Kokkinos, F., Lefkimmiatis, S.: Iterative joint image demosaicking and denoising using a residual denoising network. IEEE Transa. Image Process. (TIP) 28(8), 4177–4188 (2019)

    Article  MathSciNet  MATH  Google Scholar 

  19. Kokkinos, F., Lefkimmiatis, S.: Iterative residual cnns for burst photography applications. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5929–5938 (2019)

    Google Scholar 

  20. Lee, H., Kim, T., Chung, T.y., Pak, D., Ban, Y., Lee, S.: Adacof: adaptive collaboration of flows for video frame interpolation. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5316–5325 (2020)

    Google Scholar 

  21. Liu, Z., Yeh, R.A., Tang, X., Liu, Y., Agarwala, A.: Video frame synthesis using deep voxel flow. In: IEEE International Conference on Computer Vision (ICCV), pp. 4463–4471 (2017)

    Google Scholar 

  22. Mahajan, D., Huang, F.C., Matusik, W., Ramamoorthi, R., Belhumeur, P.: Moving gradients: a path-based method for plausible image interpolation. ACM Trans. Graph. (TOG) 28(3), 1–11 (2009)

    Article  Google Scholar 

  23. Nah, S., Hyun Kim, T., Mu Lee, K.: Deep multi-scale convolutional neural network for dynamic scene deblurring. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3883–3891 (2017)

    Google Scholar 

  24. Niklaus, S., Liu, F.: Softmax splatting for video frame interpolation. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5437–5446 (2020)

    Google Scholar 

  25. Niklaus, S., Mai, L., Liu, F.: Video frame interpolation via adaptive separable convolution. In: IEEE International Conference on Computer Vision (ICCV), pp. 261–270 (2017)

    Google Scholar 

  26. Park, J., Ko, K., Lee, C., Kim, C.: BMBC: bilateral motion estimation with bilateral cost volume for video interpolation. In: European Conference on Computer Vision (ECCV), vol. 12359, pp. 109–125 (2020). https://doi.org/10.1007/978-3-030-58568-6_7

  27. Park, J., Lee, C., Kim, C.S.: Asymmetric bilateral motion estimation for video frame interpolation. In: IEEE International Conference on Computer Vision (ICCV), pp. 14539–14548 (2021)

    Google Scholar 

  28. Perazzi, F., Pont-Tuset, J., McWilliams, B., Van Gool, L., Gross, M., Sorkine-Hornung, A.: A benchmark dataset and evaluation methodology for video object segmentation. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 724–732 (2016)

    Google Scholar 

  29. Ronneberger, O., Fischer, P., Brox, T.: U-net: Convolutional networks for biomedical image segmentation. In: International Conference on Medical Image Computing and Computer-assisted Intervention (MICCAI), pp. 234–241 (2015). https://doi.org/10.1007/978-3-319-24574-4_28

  30. Shi, Z., Liu, X., Shi, K., Dai, L., Chen, J.: Video frame interpolation via generalized deformable convolution. IEEE Trans. Multimedia (TMM) 24, 426–439 (2021)

    Article  Google Scholar 

  31. Shi, Z., Xu, X., Liu, X., Chen, J., Yang, M.H.: Video frame interpolation transformer. Arxiv preprint, 2111.13817 [cs.CV] (2021)

    Google Scholar 

  32. Sim, H., Oh, J., Kim, M.: Xvfi: Extreme video frame interpolation. In: IEEE International Conference on Computer Vision (ICCV), pp. 14489–14498 (2021)

    Google Scholar 

  33. Soomro, K., Zamir, A.R., Shah, M.: Ucf101: A dataset of 101 human actions classes from videos in the wild. Arxiv preprint, 1212.0402 [cs.CV] (2012)

    Google Scholar 

  34. Su, S., Delbracio, M., Wang, J., Sapiro, G., Heidrich, W., Wang, O.: Deep video deblurring for hand-held cameras. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1279–1288 (2017)

    Google Scholar 

  35. Sun, D., Yang, X., Liu, M.Y., Kautz, J.: Pwc-net: Cnns for optical flow using pyramid, warping, and cost volume. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8934–8943 (2018)

    Google Scholar 

  36. Sun, L., Dong, W., Li, X., Wu, J., Li, L., Shi, G.: Deep maximum a posterior estimator for video denoising. Int. J. Comput. Vis. (IJCV) 129(10), 2827–2845 (2021). https://doi.org/10.1007/s11263-021-01510-7

    Article  Google Scholar 

  37. Teed, Z., Deng, J.: Raft: recurrent all-pairs field transforms for optical flow. In: European Conference on Computer Vision (ECCV), vol. 12347, pp. 402–419 (2020). https://doi.org/10.1007/978-3-030-58536-5_24

  38. Wang, X., et al.: ESRGAN: enhanced super-resolution generative adversarial networks. In: European Conference on Computer Vision Workshops (ECCVW), vol. 11133, pp. 63–79 (2018)

    Google Scholar 

  39. Werlberger, M., Pock, T., Unger, M., Bischof, H.: Optical flow guided tv-l 1 video interpolation and restoration. In: Computer Vision and Pattern Recognition workshops (CVPRW), pp. 273–286 (2011)

    Google Scholar 

  40. Wu, Y., He, K.: Group normalization. In: European Conference on Computer Vision (ECCV), vol. 11217, pp. 3–19 (2018)

    Google Scholar 

  41. Xu, X., Siyao, L., Sun, W., Yin, Q., Yang, M.H.: Quadratic video interpolation. Adv. Neural Inf. Process. Syst. (NeurIPS) 32, 1645–1654 (2019)

    Google Scholar 

  42. Xue, T., Chen, B., Wu, J., Wei, D., Freeman, W.T.: Video enhancement with task-oriented flow. Int. J. Comput. Vis. (IJCV) 127(8), 1106–1125 (2019). https://doi.org/10.1007/s11263-018-01144-2

    Article  Google Scholar 

  43. Yu, Z., Li, H., Wang, Z., Hu, Z., Chen, C.W.: Multi-level video frame interpolation: exploiting the interaction among different levels. IEEE Trans. Circuits Syst. Video Technol. 23(7), 1235–1248 (2013)

    Article  Google Scholar 

  44. Yu, Z., et al.: Training weakly supervised video frame interpolation with events. In: IEEE International Conference on Computer Vision, (ICCV), pp. 14589–14598 (2021)

    Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Xijun Chen .

Editor information

Editors and Affiliations

1 Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary material 1 (pdf 2510 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

Yu, Z., Zhang, Y., Xiang, X., Zou, D., Chen, X., Ren, J.S. (2022). Deep Bayesian Video Frame Interpolation. 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 13675. Springer, Cham. https://doi.org/10.1007/978-3-031-19784-0_9

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-19784-0_9

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-19783-3

  • Online ISBN: 978-3-031-19784-0

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics