Disentangling random and cyclic effects in time-lapse sequences

Abstract

Time-lapse image sequences offer visually compelling insights into dynamic processes that are too slow to observe in real time. However, playing a long time-lapse sequence back as a video often results in distracting flicker due to random effects, such as weather, as well as cyclic effects, such as the day-night cycle. We introduce the problem of disentangling time-lapse sequences in a way that allows separate, after-the-fact control of overall trends, cyclic effects, and random effects in the images, and describe a technique based on data-driven generative models that achieves this goal. This enables us to "re-render" the sequences in ways that would not be possible with the input images alone. For example, we can stabilize a long sequence to focus on plant growth over many months, under selectable, consistent weather.

Our approach is based on Generative Adversarial Networks (GAN) that are conditioned with the time coordinate of the time-lapse sequence. Our architecture and training procedure are designed so that the networks learn to model random variations, such as weather, using the GAN's latent space, and to disentangle overall trends and cyclic variations by feeding the conditioning time label to the model using Fourier features with specific frequencies.

We show that our models are robust to defects in the training data, enabling us to amend some of the practical difficulties in capturing long time-lapse sequences, such as temporary occlusions, uneven frame spacing, and missing frames.

References

1. Anokhin, I., Solovev, P., Korzhenkov, D., Kharlamov, A., Khakhulin, T., Silvestrov, A., Nikolenko, S., Lempitsky, V., and Sterkin, G. (2020). High-resolution daytime translation without domain labels. In Proc. CVPR.
2. Brock, A., Donahue, J., and Simonyan, K. (2019). Large scale gan training for high fidelity natural image synthesis. In Proc. ICLR.
3. Choi, Y., Uh, Y., Yoo, J., and Ha, J.-W. (2020). Stargan v2: Diverse image synthesis for multiple domains. In Proc. CVPR.
4. Chong, M. J., Chu, W.-S., Kumar, A., and Forsyth, D. (2021). Retrieve in style: Unsupervised facial feature transfer and retrieval. In Proc. ICCV.
5. Clark, A., Donahue, J., and Simonyan, K. (2019). Efficient video generation on complex datasets. CoRR, abs/1907.06571.
6. Collins, E., Bala, R., Price, B., and Süsstrunk, S. (2020). Editing in style: Uncovering the local semantics of GANs. In Proc. CVPR.
7. Colton, S. and Ferrer, B. P. (2021). Ganlapse generative photography. In Proc. International Conference on Computational Creativity.
8. Dinh, L., Sohl-Dickstein, J., and Bengio, S. (2017). Density estimation using Real NVP. In Proc. ICLR.
9. Endo, Y., Kanamori, Y., and Kuriyama, S. (2019). Animating landscape: self-supervised learning of decoupled motion and appearance for single-image video synthesis. In Proc. SIGGRAPH ASIA 2019.
10. Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., and Bengio, Y. (2014). Generative Adversarial Networks. In Proc. NIPS.
11. Härkönen, E., Hertzmann, A., Lehtinen, J., and Paris, S. (2020). GANSpace: Discovering interpretable GAN controls. In Proc. NeurIPS.
12. Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., and Hochreiter, S. (2017). GANs trained by a two time-scale update rule converge to a local nash equilibrium. In Proceedings of the 31st International Conference on Neural Information Processing Systems, NIPS'17, page 6629--6640, Red Hook, NY, USA. Curran Associates Inc.
13. Ho, J., Jain, A., and Abbeel, P. (2020). Denoising diffusion probabilistic models. In Proc. NeurIPS.
14. Horita, D. and Yanai, K. (2020). Ssa-gan: End-to-end time-lapse video generation with spatial self-attention. In Proc. ACPR.
15. Huang, X., Mallya, A., Wang, T.-C., and Liu, M.-Y. (2021). Multimodal conditional image synthesis with product-of-experts GANs. CoRR, abs/2112.05130.
16. Jacobs, N., Burgin, W., Fridrich, N., Abrams, A., Miskell, K., Braswell, B. H., Richardson, A. D., and Pless, R. (2009). The global network of outdoor webcams: Properties and applications. In ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems (ACM SIGSPATIAL).
17. Jacobs, N., Roman, N., and Pless, R. (2007). Consistent temporal variations in many outdoor scenes. In Proc. CVPR.
18. Kafri, O., Patashnik, O., Alaluf, Y., and Cohen-Or, D. (2021). Stylefusion: A generative model for disentangling spatial segments. CoRR, abs/2107.07437.
19. Karacan, L., Akata, Z., Erdem, A., and Erdem, E. (2019). Manipulating attributes of natural scenes via hallucination. In Proc. TOG.
20. Karras, T., Aittala, M., Hellsten, J., Laine, S., Lehtinen, J., and Aila, T. (2020a). Training generative adversarial networks with limited data. In Proc. NeurIPS.
21. Karras, T., Aittala, M., Laine, S., Härkönen, E., Hellsten, J., Lehtinen, J., and Aila, T. (2021). Alias-free generative adversarial networks. In Proc. NeurIPS.
22. Karras, T., Laine, S., and Aila, T. (2019). A style-based generator architecture for generative adversarial networks. In Proc. CVPR.
23. Karras, T., Laine, S., Aittala, M., Hellsten, J., Lehtinen, J., and Aila, T. (2020b). Analyzing and improving the image quality of StyleGAN. In Proc. CVPR.
24. Kim, J., Kim, M., Kang, H., and Lee, K. (2020). U-gat-it: Unsupervised generative attentional networks with adaptive layer-instance normalization for image-to-image translation. In Proc. ICLR.
25. Kingma, D. P. and Dhariwal, P. (2018). Glow: Generative flow with invertible 1x1 convolutions. In Proc. NeurIPS.
26. Kingma, D. P. and Welling, M. (2014). Auto-encoding variational bayes. In Proc. ICLR.
27. Logacheva, E., Suvorov, R., Khomenko, O., Mashikhin, A., and Lempitsky, V. (2020). Deeplandscape: Adversarial modeling of landscape videos. In Proc. ECCV.
28. Martin-Brualla, R., Gallup, D., and Seitz, S. M. (2015). Time-lapse mining from internet photos. In Proc. TOG.
29. Mirza, M. and Osindero, S. (2014). Conditional generative adversarial nets. CoRR, abs/1411.1784.
30. Miyato, T. and Koyama, M. (2018). cgans with projection discriminator. In Proc. ICLR.
31. Nam, S., Ma, C., Chai, M., Brendel, W., Xu, N., and Kim, S. J. (2019). End-to-end time-lapse video synthesis from a single outdoor image. In Proc. CVPR.
32. Park, T., Liu, M.-Y., Wang, T., and Zhu, J.-Y. (2019). Semantic image synthesis with spatially-adaptive normalization. In Proc. CVPR.
33. Park, T., Zhu, J.-Y., Wang, O., Lu, J., Shechtman, E., Efros, A. A., and Zhang, R. (2020). Swapping autoencoder for deep image manipulation. In Proc. NeurIPS.
34. Sohl-Dickstein, J., Weiss, E. A., Maheswaranathan, N., and Ganguli, S. (2015). Deep unsupervised learning using nonequilibrium thermodynamics. In Proc. ICML.
35. Song, Y. and Ermon, S. (2019). Generative modeling by estimating gradients of the data distribution. In Proc. NeurIPS.
36. Sun, J., Shen, Z., Wang, Y., Bao, H., and Zhou, X. (2021). LoFTR: Detector-free local feature matching with transformers. In Proc. CVPR.
37. Tancik, M., Srinivasan, P. P., Mildenhall, B., Fridovich-Keil, S., Raghavan, N., Singhal, U., Ramamoorthi, R., Barron, J. T., and Ng, R. (2020). Fourier features let networks learn high frequency functions in low dimensional domains. In Proc. NeurIPS.
38. Tulyakov, S., Liu, M.-Y., Yang, X., and Kautz, J. (2018). MoCoGAN: Decomposing motion and content for video generation. In Proc. CVPR.
39. van den Oord, A., Kalchbrenner, N., and Kavukcuoglu, K. (2016a). Pixel recurrent neural networks. In Proc. ICML.
40. van den Oord, A., Kalchbrenner, N., Vinyals, O., Espeholt, L., Graves, A., and Kavukcuoglu, K. (2016b). Conditional image generation with PixelCNN decoders. In Proc. NIPS.
41. Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., and Polosukhin, I. (2017). Attention is all you need. In Proc. NeurIPS.
42. Wang, T.-C., Liu, M.-Y., Tao, A., Liu, G., Kautz, J., and Catanzaro, B. (2019). Few-shot video-to-video synthesis. In Proc. NeurIPS.
43. Wang, T.-C., Liu, M.-Y., Zhu, J.-Y., Liu, G., Tao, A., Kautz, J., and Catanzaro, B. (2018). Video-to-video synthesis. In Proc. NeurIPS.
44. Xiong, W., Luo, W., Ma, L., Liu, W., and Luo, J. (2018). Learning to generate time-lapse videos using multi-stage dynamic generative adversarial networks. In Proc. CVPR.
45. Zhu, J.-Y., Park, T., Isola, P., and Efros, A. A. (2017). Unpaired image-to-image translation using cycle-consistent adversarial networks. In Proc. ICCV.

Index Terms

• Computing methodologies

  • Artificial intelligence

    • Computer vision

      • Computer vision representations

        • Image representations

  • Computer graphics

  • Machine learning

    • Machine learning approaches

      • Learning latent representations