{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T17:03:06Z","timestamp":1791910986867,"version":"4.3.4"},"publisher-location":"Cham","reference-count":94,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030585976","type":"print"},{"value":"9783030585983","type":"electronic"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020]]},"DOI":"10.1007\/978-3-030-58598-3_22","type":"book-chapter","created":{"date-parts":[[2020,11,6]],"date-time":"2020-11-06T11:03:52Z","timestamp":1604660632000},"page":"359-378","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":66,"title":["World-Consistent Video-to-Video Synthesis"],"prefix":"10.1007","author":[{"given":"Arun","family":"Mallya","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ting-Chun","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Karan","family":"Sapra","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ming-Yu","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2020,11,7]]},"reference":[{"key":"22_CR1","unstructured":"OpenSfM. https:\/\/github.com\/mapillary\/OpenSfM"},{"key":"22_CR2","doi-asserted-by":"crossref","unstructured":"Aliev, K.A., Ulyanov, D., Lempitsky, V.: Neural point-based graphics. arXiv preprint arXiv:1906.08240 (2019)","DOI":"10.1007\/978-3-030-58542-6_42"},{"key":"22_CR3","unstructured":"Benaim, S., Wolf, L.: One-shot unsupervised cross domain translation. In: Conference on Neural Information Processing Systems (NeurIPS) (2018)"},{"key":"22_CR4","doi-asserted-by":"crossref","unstructured":"Bonneel, N., Tompkin, J., Sunkavalli, K., Sun, D., Paris, S., Pfister, H.: Blind video temporal consistency. ACM Trans. Graph. (TOG) (2015)","DOI":"10.1145\/2816795.2818107"},{"key":"22_CR5","doi-asserted-by":"crossref","unstructured":"Bousmalis, K., Silberman, N., Dohan, D., Erhan, D., Krishnan, D.: Unsupervised pixel-level domain adaptation with generative adversarial networks. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.18"},{"key":"22_CR6","unstructured":"Brock, A., Donahue, J., Simonyan, K.: Large scale GAN training for high fidelity natural image synthesis. In: International Conference on Learning Representations (ICLR) (2019)"},{"key":"22_CR7","doi-asserted-by":"crossref","unstructured":"Cao, Z., Hidalgo, G., Simon, T., Wei, S.E., Sheikh, Y.: OpenPose: realtime multi-person 2D pose estimation using Part Affinity Fields. arXiv preprint arXiv:1812.08008 (2018)","DOI":"10.1109\/CVPR.2017.143"},{"key":"22_CR8","doi-asserted-by":"crossref","unstructured":"Chan, C., Ginosar, S., Zhou, T., Efros, A.A.: Everybody dance now. In: IEEE International Conference on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.00603"},{"key":"22_CR9","doi-asserted-by":"crossref","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","volume":"40","author":"LC Chen","year":"2017","unstructured":"Chen, L.C., Papandreou, G., Kokkinos, I., Murphy, K., Yuille, A.L.: DeepLab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs. IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI) 40, 834\u2013848 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI)"},{"key":"22_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"833","DOI":"10.1007\/978-3-030-01234-2_49","volume-title":"Computer Vision \u2013 ECCV 2018","author":"L-C Chen","year":"2018","unstructured":"Chen, L.-C., Zhu, Y., Papandreou, G., Schroff, F., Adam, H.: Encoder-decoder with atrous separable convolution for semantic image segmentation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11211, pp. 833\u2013851. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01234-2_49"},{"key":"22_CR11","doi-asserted-by":"crossref","unstructured":"Chen, Q., Koltun, V.: Photographic image synthesis with cascaded refinement networks. In: IEEE International Conference on Computer Vision (ICCV) (2017)","DOI":"10.1109\/ICCV.2017.168"},{"key":"22_CR12","doi-asserted-by":"crossref","unstructured":"Chen, Y., Pan, Y., Yao, T., Tian, X., Mei, T.: Mocycle-GAN: unpaired video-to-video translation. In: ACM International Conference on Multimedia (MM) (2019)","DOI":"10.1145\/3343031.3350937"},{"key":"22_CR13","doi-asserted-by":"crossref","unstructured":"Choi, I., Gallo, O., Troccoli, A., Kim, M.H., Kautz, J.: Extreme view synthesis. In: IEEE International Conference on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.00787"},{"key":"22_CR14","doi-asserted-by":"crossref","unstructured":"Choi, Y., Choi, M., Kim, M., Ha, J.W., Kim, S., Choo, J.: StarGAN: unified generative adversarial networks for multi-domain image-to-image translation. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00916"},{"key":"22_CR15","doi-asserted-by":"crossref","unstructured":"Cordts, M., et al.: The Cityscapes dataset for semantic urban scene understanding. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.350"},{"key":"22_CR16","doi-asserted-by":"crossref","unstructured":"Dai, A., Chang, A.X., Savva, M., Halber, M., Funkhouser, T., Nie\u00dfner, M.: ScanNet: Richly-annotated 3D reconstructions of indoor scenes. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.261"},{"key":"22_CR17","unstructured":"Denton, E.L., Birodkar, V.: Unsupervised learning of disentangled representations from video. In: Conference on Neural Information Processing Systems (NeurIPS) (2017)"},{"key":"22_CR18","unstructured":"Dosovitskiy, A., Ros, G., Codevilla, F., Lopez, A., Koltun, V.: CARLA: an open urban driving simulator. In: Conference on Robot Learning (CoRL) (2017)"},{"key":"22_CR19","unstructured":"Finn, C., Goodfellow, I., Levine, S.: Unsupervised learning for physical interaction through video prediction. In: Conference on Neural Information Processing Systems (NeurIPS) (2016)"},{"key":"22_CR20","doi-asserted-by":"crossref","unstructured":"Flynn, J., et al.: Deepview: view synthesis with learned gradient descent. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00247"},{"key":"22_CR21","doi-asserted-by":"crossref","unstructured":"Flynn, J., Neulander, I., Philbin, J., Snavely, N.: DeepStereo: learning to predict new views from the world\u2019s imagery. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.595"},{"key":"22_CR22","unstructured":"Gafni, O., Wolf, L., Taigman, Y.: Vid2Game: controllable characters extracted from real-world videos. In: International Conference on Learning Representations (ICLR) (2020)"},{"key":"22_CR23","doi-asserted-by":"crossref","unstructured":"Golyanik, V., Kim, K., Maier, R., Nie\u00dfner, M., Stricker, D., Kautz, J.: Multiframe scene flow with piecewise rigid motion. In: International Conference on 3D Vision (3DV) (2017)","DOI":"10.1109\/3DV.2017.00039"},{"key":"22_CR24","unstructured":"Goodfellow, I., et al.: Generative adversarial networks. In: Conference on Neural Information Processing Systems (NeurIPS) (2014)"},{"key":"22_CR25","doi-asserted-by":"crossref","unstructured":"G\u00fcler, R.A., Neverova, N., Kokkinos, I.: DensePose: dense human pose estimation in the wild. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00762"},{"key":"22_CR26","unstructured":"Gulrajani, I., Ahmed, F., Arjovsky, M., Dumoulin, V., Courville, A.C.: Improved training of Wasserstein GANs. In: Conference on Neural Information Processing Systems (NeurIPS) (2017)"},{"key":"22_CR27","doi-asserted-by":"crossref","unstructured":"Hao, Z., Huang, X., Belongie, S.: Controllable video generation with sparse trajectories. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00819"},{"key":"22_CR28","first-page":"1","volume":"37","author":"P Hedman","year":"2018","unstructured":"Hedman, P., Philip, J., Price, T., Frahm, J.M., Drettakis, G., Brostow, G.: Deep blending for free-viewpoint image-based rendering. ACM Trans. Graph. (TOG) 37, 1\u201315 (2018)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"22_CR29","unstructured":"Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., Hochreiter, S.: GANs trained by a two time-scale update rule converge to a local Nash equilibrium. In: Conference on Neural Information Processing Systems (NeurIPS) (2017)"},{"key":"22_CR30","unstructured":"Hu, Q., Waelchli, A., Portenier, T., Zwicker, M., Favaro, P.: Video synthesis from a single image and motion stroke. arXiv preprint arXiv:1812.01874 (2018)"},{"key":"22_CR31","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"179","DOI":"10.1007\/978-3-030-01219-9_11","volume-title":"Computer Vision \u2013 ECCV 2018","author":"X Huang","year":"2018","unstructured":"Huang, X., Liu, M.-Y., Belongie, S., Kautz, J.: Multimodal unsupervised image-to-image translation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11207, pp. 179\u2013196. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01219-9_11"},{"key":"22_CR32","doi-asserted-by":"crossref","unstructured":"Isola, P., Zhu, J.Y., Zhou, T., Efros, A.A.: Image-to-image translation with conditional adversarial networks. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.632"},{"key":"22_CR33","doi-asserted-by":"crossref","unstructured":"Johnson, J., Gupta, A., Fei-Fei, L.: Image generation from scene graphs. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00133"},{"key":"22_CR34","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/2980179.2980251","volume":"35","author":"NK Kalantari","year":"2016","unstructured":"Kalantari, N.K., Wang, T.C., Ramamoorthi, R.: Learning-based view synthesis for light field cameras. ACM Trans. Graph. (TOG) 35, 1\u201310 (2016)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"22_CR35","unstructured":"Kalchbrenner, N., et al.: Video pixel networks. In: International Conference on Machine Learning (ICML) (2017)"},{"key":"22_CR36","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3355089.3356557","volume":"38","author":"AS Kaplanyan","year":"2019","unstructured":"Kaplanyan, A.S., Sochenov, A., Leimk\u00fchler, T., Okunev, M., Goodall, T., Rufo, G.: DeepFovea: neural reconstruction for foveated rendering and video compression using learned statistics of natural videos. ACM Trans. Graph. (TOG) 38, 1\u201313 (2019)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"22_CR37","unstructured":"Karras, T., Aila, T., Laine, S., Lehtinen, J.: Progressive growing of GANs for improved quality, stability, and variation. In: International Conference on Learning Representations (ICLR) (2018)"},{"key":"22_CR38","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., Aila, T.: A style-based generator architecture for generative adversarial networks. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00453"},{"key":"22_CR39","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"179","DOI":"10.1007\/978-3-030-01267-0_11","volume-title":"Computer Vision \u2013 ECCV 2018","author":"W-S Lai","year":"2018","unstructured":"Lai, W.-S., Huang, J.-B., Wang, O., Shechtman, E., Yumer, E., Yang, M.-H.: Learning blind video temporal consistency. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11219, pp. 179\u2013195. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01267-0_11"},{"key":"22_CR40","unstructured":"Lee, A.X., Zhang, R., Ebert, F., Abbeel, P., Finn, C., Levine, S.: Stochastic adversarial video prediction. arXiv preprint arXiv:1804.01523 (2018)"},{"key":"22_CR41","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"36","DOI":"10.1007\/978-3-030-01246-5_3","volume-title":"Computer Vision \u2013 ECCV 2018","author":"H-Y Lee","year":"2018","unstructured":"Lee, H.-Y., Tseng, H.-Y., Huang, J.-B., Singh, M., Yang, M.-H.: Diverse image-to-image translation via disentangled representations. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11205, pp. 36\u201352. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01246-5_3"},{"key":"22_CR42","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"609","DOI":"10.1007\/978-3-030-01240-3_37","volume-title":"Computer Vision \u2013 ECCV 2018","author":"Y Li","year":"2018","unstructured":"Li, Y., Fang, C., Yang, J., Wang, Z., Lu, X., Yang, M.-H.: Flow-grounded spatial-temporal video prediction from still images. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11213, pp. 609\u2013625. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01240-3_37"},{"key":"22_CR43","doi-asserted-by":"crossref","unstructured":"Li, Z., et al.: Learning the depths of moving people by watching frozen people. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00465"},{"key":"22_CR44","doi-asserted-by":"crossref","unstructured":"Li, Z., Snavely, N.: MegaDepth: learning single-view depth prediction from internet photos. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00218"},{"key":"22_CR45","doi-asserted-by":"crossref","unstructured":"Liang, X., Lee, L., Dai, W., Xing, E.P.: Dual motion GAN for future-flow embedded video prediction. In: Conference on Neural Information Processing Systems (NeurIPS) (2017)","DOI":"10.1109\/ICCV.2017.194"},{"key":"22_CR46","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1007\/978-3-030-01252-6_6","volume-title":"Computer Vision \u2013 ECCV 2018","author":"G Liu","year":"2018","unstructured":"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\u2013105. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01252-6_6"},{"key":"22_CR47","unstructured":"Liu, M.Y., Breuel, T., Kautz, J.: Unsupervised image-to-image translation networks. In: Conference on Neural Information Processing Systems (NeurIPS) (2017)"},{"key":"22_CR48","doi-asserted-by":"crossref","unstructured":"Liu, M.Y., et al.: Few-shot unsupervised image-to-image translation. In: IEEE International Conference on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.01065"},{"key":"22_CR49","unstructured":"Liu, X., Yin, G., Shao, J., Wang, X., et al.: Learning to predict layout-to-image conditional convolutions for semantic image synthesis. In: Conference on Neural Information Processing Systems (NeurIPS) (2019)"},{"key":"22_CR50","doi-asserted-by":"crossref","unstructured":"Longuet-Higgins, H.C.: A computer algorithm for reconstructing a scene from two projections. Nature (1981)","DOI":"10.1038\/293133a0"},{"key":"22_CR51","unstructured":"Lotter, W., Kreiman, G., Cox, D.: Deep predictive coding networks for video prediction and unsupervised learning. In: International Conference on Learning Representations (ICLR) (2017)"},{"key":"22_CR52","unstructured":"Mathieu, M., Couprie, C., LeCun, Y.: Deep multi-scale video prediction beyond mean square error. In: International Conference on Learning Representations (ICLR) (2016)"},{"key":"22_CR53","doi-asserted-by":"crossref","unstructured":"Meshry, M., et al.: Neural rerendering in the wild. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00704"},{"key":"22_CR54","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3306346.3322980","volume":"38","author":"B Mildenhall","year":"2019","unstructured":"Mildenhall, B., et al.: Local light field fusion: practical view synthesis with prescriptive sampling guidelines. ACM Trans. Graph. (TOG) 38, 1\u201314 (2019)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"22_CR55","unstructured":"Miyato, T., Koyama, M.: cGANs with projection discriminator. In: International Conference on Learning Representations (ICLR) (2018)"},{"key":"22_CR56","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"746","DOI":"10.1007\/978-3-642-33715-4_54","volume-title":"Computer Vision \u2013 ECCV 2012","author":"N Silberman","year":"2012","unstructured":"Silberman, N., Hoiem, D., Kohli, P., Fergus, R.: Indoor segmentation and support inference from RGBD images. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7576, pp. 746\u2013760. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-33715-4_54"},{"key":"22_CR57","unstructured":"Odena, A., Olah, C., Shlens, J.: Conditional image synthesis with auxiliary classifier GANs. In: International Conference on Machine Learning (ICML) (2017)"},{"key":"22_CR58","doi-asserted-by":"crossref","unstructured":"Pan, J., et al.: Video generation from single semantic label map. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00385"},{"key":"22_CR59","doi-asserted-by":"crossref","unstructured":"Park, T., Liu, M.Y., Wang, T.C., Zhu, J.Y.: Semantic image synthesis with spatially-adaptive normalization. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00244"},{"key":"22_CR60","doi-asserted-by":"crossref","unstructured":"Qi, X., Chen, Q., Jia, J., Koltun, V.: Semi-parametric image synthesis. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00918"},{"key":"22_CR61","unstructured":"Reed, S., Akata, Z., Yan, X., Logeswaran, L., Schiele, B., Lee, H.: Generative adversarial text to image synthesis. In: International Conference on Machine Learning (ICML) (2016)"},{"key":"22_CR62","doi-asserted-by":"crossref","unstructured":"Saito, M., Matsumoto, E., Saito, S.: Temporal generative adversarial nets with singular value clipping. In: IEEE International Conference on Computer Vision (ICCV) (2017)","DOI":"10.1109\/ICCV.2017.308"},{"key":"22_CR63","doi-asserted-by":"crossref","unstructured":"Shrivastava, A., Pfister, T., Tuzel, O., Susskind, J., Wang, W., Webb, R.: Learning from simulated and unsupervised images through adversarial training. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.241"},{"key":"22_CR64","doi-asserted-by":"crossref","unstructured":"Sitzmann, V., Thies, J., Heide, F., Nie\u00dfner, M., Wetzstein, G., Zollhofer, M.: Deepvoxels: Learning persistent 3d feature embeddings. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00254"},{"key":"22_CR65","doi-asserted-by":"crossref","unstructured":"Srinivasan, P.P., Wang, T., Sreelal, A., Ramamoorthi, R., Ng, R.: Learning to synthesize a 4D RGBD light field from a single image. In: IEEE International Conference on Computer Vision (ICCV) (2017)","DOI":"10.1109\/ICCV.2017.246"},{"key":"22_CR66","unstructured":"Srivastava, N., Mansimov, E., Salakhudinov, R.: Unsupervised learning of video representations using LSTMs. In: International Conference on Machine Learning (ICML) (2015)"},{"key":"22_CR67","unstructured":"Taigman, Y., Polyak, A., Wolf, L.: Unsupervised cross-domain image generation. In: International Conference on Learning Representations (ICLR) (2017)"},{"key":"22_CR68","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3306346.3323035","volume":"38","author":"J Thies","year":"2019","unstructured":"Thies, J., Zollh\u00f6fer, M., Nie\u00dfner, M.: Deferred neural rendering: image synthesis using neural textures. ACM Trans. Graph. (TOG) 38, 1\u201312 (2019)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"22_CR69","doi-asserted-by":"crossref","first-page":"137","DOI":"10.1007\/BF00129684","volume":"9","author":"C Tomasi","year":"1992","unstructured":"Tomasi, C., Kanade, T.: Shape and motion from image streams under orthography: a factorization method. Int. J. Comput. Vis. (IJCV) 9, 137\u2013154 (1992)","journal-title":"Int. J. Comput. Vis. (IJCV)"},{"key":"22_CR70","doi-asserted-by":"crossref","unstructured":"Tulyakov, S., Liu, M.Y., Yang, X., Kautz, J.: MoCoGAN: decomposing motion and content for video generation. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00165"},{"key":"22_CR71","doi-asserted-by":"crossref","unstructured":"Vedula, S., Baker, S., Rander, P., Collins, R., Kanade, T.: Three-dimensional scene flow. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (1999)","DOI":"10.1109\/ICCV.1999.790293"},{"key":"22_CR72","unstructured":"Villegas, R., Yang, J., Hong, S., Lin, X., Lee, H.: Decomposing motion and content for natural video sequence prediction. In: International Conference on Learning Representations (ICLR) (2017)"},{"key":"22_CR73","unstructured":"Vondrick, C., Pirsiavash, H., Torralba, A.: Generating videos with scene dynamics. In: Conference on Neural Information Processing Systems (NeurIPS) (2016)"},{"key":"22_CR74","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"835","DOI":"10.1007\/978-3-319-46478-7_51","volume-title":"Computer Vision \u2013 ECCV 2016","author":"J Walker","year":"2016","unstructured":"Walker, J., Doersch, C., Gupta, A., Hebert, M.: An uncertain future: forecasting from static images using variational autoencoders. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9911, pp. 835\u2013851. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46478-7_51"},{"key":"22_CR75","doi-asserted-by":"crossref","unstructured":"Walker, J., Marino, K., Gupta, A., Hebert, M.: The pose knows: video forecasting by generating pose futures. In: IEEE International Conference on Computer Vision (ICCV) (2017)","DOI":"10.1109\/ICCV.2017.361"},{"key":"22_CR76","unstructured":"Wang, T.C., Liu, M.Y., Tao, A., Liu, G., Kautz, J., Catanzaro, B.: Few-shot video-to-video synthesis. In: Conference on Neural Information Processing Systems (NeurIPS) (2019)"},{"key":"22_CR77","unstructured":"Wang, T.C., et al.: Video-to-video synthesis. In: Conference on Neural Information Processing Systems (NeurIPS) (2018)"},{"key":"22_CR78","doi-asserted-by":"crossref","unstructured":"Wang, T.C., Liu, M.Y., Zhu, J.Y., Tao, A., Kautz, J., Catanzaro, B.: High-resolution image synthesis and semantic manipulation with conditional GANs. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00917"},{"key":"22_CR79","doi-asserted-by":"crossref","unstructured":"Wiles, O., Gkioxari, G., Szeliski, R., Johnson, J.: SynSin: end-to-end view synthesis from a single image. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.00749"},{"key":"22_CR80","unstructured":"Wu, Y., Kirillov, A., Massa, F., Lo, W.Y., Girshick, R.: Detectron2 (2019). https:\/\/github.com\/facebookresearch\/detectron2"},{"key":"22_CR81","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1016\/j.patcog.2019.01.006","volume":"90","author":"Z Wu","year":"2019","unstructured":"Wu, Z., Shen, C., Van Den Hengel, A.: Wider or deeper: revisiting the resnet model for visual recognition. Pattern Recogn. 90, 119\u2013133 (2019)","journal-title":"Pattern Recogn."},{"key":"22_CR82","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"842","DOI":"10.1007\/978-3-319-46493-0_51","volume-title":"Computer Vision \u2013 ECCV 2016","author":"J Xie","year":"2016","unstructured":"Xie, J., Girshick, R., Farhadi, A.: Deep3D: fully automatic 2D-to-3D video conversion with deep convolutional neural networks. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 842\u2013857. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46493-0_51"},{"key":"22_CR83","doi-asserted-by":"crossref","unstructured":"Xie, S., Tu, Z.: Holistically-nested edge detection. In: IEEE International Conference on Computer Vision (ICCV) (2015)","DOI":"10.1109\/ICCV.2015.164"},{"key":"22_CR84","doi-asserted-by":"crossref","unstructured":"Xu, T., et al.: AttnGAN: fine-grained text to image generation with attentional generative adversarial networks. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00143"},{"key":"22_CR85","unstructured":"Xue, T., Wu, J., Bouman, K., Freeman, B.: Visual dynamics: probabilistic future frame synthesis via cross convolutional networks. In: Conference on Neural Information Processing Systems (NeurIPS) (2016)"},{"key":"22_CR86","doi-asserted-by":"crossref","unstructured":"Yao, C.H., Chang, C.Y., Chien, S.Y.: Occlusion-aware video temporal consistency. In: ACM International Conference on Multimedia (MM) (2017)","DOI":"10.1145\/3123266.3123363"},{"key":"22_CR87","unstructured":"Zhang, H., Goodfellow, I., Metaxas, D., Odena, A.: Self-attention generative adversarial networks. In: International Conference on Machine Learning (ICML) (2019)"},{"key":"22_CR88","doi-asserted-by":"crossref","unstructured":"Zhang, H., et al.: StackGAN: text to photo-realistic image synthesis with stacked generative adversarial networks. In: IEEE International Conference on Computer Vision (ICCV) (2017)","DOI":"10.1109\/ICCV.2017.629"},{"key":"22_CR89","doi-asserted-by":"crossref","unstructured":"Zhao, B., Meng, L., Yin, W., Sigal, L.: Image generation from layout. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00878"},{"key":"22_CR90","doi-asserted-by":"crossref","unstructured":"Zhao, H., Shi, J., Qi, X., Wang, X., Jia, J.: Pyramid scene parsing network. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.660"},{"key":"22_CR91","doi-asserted-by":"crossref","unstructured":"Zhou, T., Tucker, R., Flynn, J., Fyffe, G., Snavely, N.: Stereo magnification: learning view synthesis using multiplane images. In: ACM SIGGRAPH (2018)","DOI":"10.1145\/3197517.3201323"},{"key":"22_CR92","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Wang, Z., Fang, C., Bui, T., Berg, T.L.: Dance dance generation: motion transfer for internet videos. arXiv preprint arXiv:1904.00129 (2019)","DOI":"10.1109\/ICCVW.2019.00153"},{"key":"22_CR93","doi-asserted-by":"crossref","unstructured":"Zhu, J.Y., Park, T., Isola, P., Efros, A.A.: Unpaired image-to-image translation using cycle-consistent adversarial networks. In: IEEE International Conference on Computer Vision (ICCV) (2017)","DOI":"10.1109\/ICCV.2017.244"},{"key":"22_CR94","doi-asserted-by":"crossref","unstructured":"Zhu, Y., et al.: Improving semantic segmentation via video propagation and label relaxation. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00906"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2020"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-58598-3_22","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,5]],"date-time":"2024-11-05T19:30:37Z","timestamp":1730835037000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-58598-3_22"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030585976","9783030585983"],"references-count":94,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-58598-3_22","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"7 November 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Glasgow","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"United Kingdom","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 August 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 August 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2020.eu\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"OpenReview","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5025","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1360","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"27% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"7","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"The conference was held virtually due to the COVID-19 pandemic.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}