{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T13:36:15Z","timestamp":1772112975954,"version":"3.50.1"},"publisher-location":"Cham","reference-count":103,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031197833","type":"print"},{"value":"9783031197840","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-19784-0_36","type":"book-chapter","created":{"date-parts":[[2022,10,30]],"date-time":"2022-10-30T14:02:50Z","timestamp":1667138570000},"page":"616-635","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":29,"title":["BlobGAN: Spatially Disentangled Scene Representations"],"prefix":"10.1007","author":[{"given":"Dave","family":"Epstein","sequence":"first","affiliation":[]},{"given":"Taesung","family":"Park","sequence":"additional","affiliation":[]},{"given":"Richard","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Eli","family":"Shechtman","sequence":"additional","affiliation":[]},{"given":"Alexei A.","family":"Efros","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,10,31]]},"reference":[{"key":"36_CR1","doi-asserted-by":"crossref","unstructured":"Abdal, R., Qin, Y., Wonka, P.: Image2StyleGAN: how to embed images into the StyleGAN latent space? In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4432\u20134441 (2019)","DOI":"10.1109\/ICCV.2019.00453"},{"issue":"3","key":"36_CR2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3447648","volume":"40","author":"R Abdal","year":"2021","unstructured":"Abdal, R., Zhu, P., Mitra, N.J., Wonka, P.: StyleFlow: attribute-conditioned exploration of StyleGAN-generated images using conditional continuous normalizing flows. ACM Trans. Graph. (TOG) 40(3), 1\u201321 (2021)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"36_CR3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3478513.3480559","volume":"40","author":"B AlBahar","year":"2021","unstructured":"AlBahar, B., Lu, J., Yang, J., Shu, Z., Shechtman, E., Huang, J.B.: Pose with style: detail-preserving pose-guided image synthesis with conditional StyleGAN. ACM Trans. Graph. 40, 1\u201311 (2021)","journal-title":"ACM Trans. Graph."},{"issue":"3","key":"36_CR4","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1145\/1531326.1531330","volume":"28","author":"C Barnes","year":"2009","unstructured":"Barnes, C., Shechtman, E., Finkelstein, A., Goldman, D.B.: PatchMatch: a randomized correspondence algorithm for structural image editing. ACM Trans. Graph. 28(3), 24 (2009)","journal-title":"ACM Trans. Graph."},{"key":"36_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"351","DOI":"10.1007\/978-3-030-58452-8_21","volume-title":"Computer Vision \u2013 ECCV 2020","author":"D Bau","year":"2020","unstructured":"Bau, D., Liu, S., Wang, T., Zhu, J.-Y., Torralba, A.: Rewriting a deep generative model. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 351\u2013369. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_21"},{"key":"36_CR6","unstructured":"Bau, D., et al.: Gan dissection: visualizing and understanding generative adversarial networks. arXiv preprint arXiv:1811.10597 (2018)"},{"key":"36_CR7","doi-asserted-by":"crossref","unstructured":"Bau, D., et al.: Seeing what a GAN cannot generate. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4502\u20134511 (2019)","DOI":"10.1109\/ICCV.2019.00460"},{"key":"36_CR8","first-page":"6027","volume":"33","author":"D Bear","year":"2020","unstructured":"Bear, D., et al.: Learning physical graph representations from visual scenes. Adv. Neural. Inf. Process. Syst. 33, 6027\u20136039 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"36_CR9","unstructured":"Biederman, I.: On the semantics of a glance at a scene (1981)"},{"key":"36_CR10","unstructured":"Brock, A., Donahue, J., Simonyan, K.: Large scale GAN training for high fidelity natural image synthesis (2018)"},{"key":"36_CR11","doi-asserted-by":"crossref","unstructured":"Brooks, T., Efros, A.A.: Hallucinating pose-compatible scenes. arXiv preprint arXiv:2112.06909 (2021)","DOI":"10.1007\/978-3-031-19787-1_29"},{"key":"36_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"509","DOI":"10.1007\/3-540-48762-X_63","volume-title":"Visual Information and Information Systems","author":"C Carson","year":"1999","unstructured":"Carson, C., Thomas, M., Belongie, S., Hellerstein, J.M., Malik, J.: Blobworld: a system for region-based image indexing and retrieval. In: Huijsmans, D.P., Smeulders, A.W.M. (eds.) VISUAL 1999. LNCS, vol. 1614, pp. 509\u2013517. Springer, Heidelberg (1999). https:\/\/doi.org\/10.1007\/3-540-48762-X_63"},{"key":"36_CR13","unstructured":"Chai, L., Wulff, J., Isola, P.: Using latent space regression to analyze and leverage compositionality in GANs. arXiv preprint arXiv:2103.10426 (2021)"},{"key":"36_CR14","doi-asserted-by":"crossref","unstructured":"Chen, Q., Koltun, V.: Photographic image synthesis with cascaded refinement networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1511\u20131520 (2017)","DOI":"10.1109\/ICCV.2017.168"},{"key":"36_CR15","doi-asserted-by":"crossref","unstructured":"Collins, E., Bala, R., Price, B., Susstrunk, S.: Editing in style: uncovering the local semantics of GANs. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5771\u20135780 (2020)","DOI":"10.1109\/CVPR42600.2020.00581"},{"key":"36_CR16","unstructured":"Denton, E.L., Chintala, S., Fergus, R., et al.: Deep generative image models using laplacian pyramid of adversarial networks. Adv. Neural Inf. Process. Syst. 28 (2015)"},{"key":"36_CR17","doi-asserted-by":"crossref","unstructured":"Goetschalckx, L., Andonian, A., Oliva, A., Isola, P.: GANalyze: toward visual definitions of cognitive image properties. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5744\u20135753 (2019)","DOI":"10.1109\/ICCV.2019.00584"},{"key":"36_CR18","unstructured":"Goodfellow, I., et al.: Generative adversarial nets. Adv. Neural Inf. Process. Syst. 27 (2014)"},{"key":"36_CR19","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"482","DOI":"10.1007\/978-3-642-15561-1_35","volume-title":"Computer Vision \u2013 ECCV 2010","author":"A Gupta","year":"2010","unstructured":"Gupta, A., Efros, A.A., Hebert, M.: Blocks world revisited: image understanding using qualitative geometry and mechanics. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010. LNCS, vol. 6314, pp. 482\u2013496. Springer, Heidelberg (2010). https:\/\/doi.org\/10.1007\/978-3-642-15561-1_35"},{"key":"36_CR20","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"297","DOI":"10.1007\/978-3-319-10584-0_20","volume-title":"Computer Vision \u2013 ECCV 2014","author":"B Hariharan","year":"2014","unstructured":"Hariharan, B., Arbel\u00e1ez, P., Girshick, R., Malik, J.: Simultaneous detection and segmentation. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8695, pp. 297\u2013312. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10584-0_20"},{"key":"36_CR21","first-page":"9841","volume":"33","author":"E H\u00e4rk\u00f6nen","year":"2020","unstructured":"H\u00e4rk\u00f6nen, E., Hertzmann, A., Lehtinen, J., Paris, S.: GANSpace: discovering interpretable GAN controls. Adv. Neural. Inf. Process. Syst. 33, 9841\u20139850 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"36_CR22","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., Girshick, R.: Masked autoencoders are scalable vision learners. arXiv preprint arXiv:2111.06377 (2021)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"36_CR23","unstructured":"He, X., Wandt, B., Rhodin, H.: Latentkeypointgan: controlling GANs via latent keypoints. arXiv preprint arXiv:2103.15812 (2021)"},{"key":"36_CR24","doi-asserted-by":"crossref","unstructured":"Hedau, V., Hoiem, D., Forsyth, D.: Recovering the spatial layout of cluttered rooms. In: 2009 IEEE 12th International Conference on Computer Vision, pp. 1849\u20131856. IEEE (2009)","DOI":"10.1109\/ICCV.2009.5459411"},{"key":"36_CR25","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. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"36_CR26","unstructured":"Higgins, I., et al.: Beta-VAE: learning basic visual concepts with a constrained variational framework (2016)"},{"issue":"4","key":"36_CR27","doi-asserted-by":"publisher","first-page":"423","DOI":"10.3758\/BF03197475","volume":"6","author":"HS Hock","year":"1978","unstructured":"Hock, H.S., Romanski, L., Galie, A., Williams, C.S.: Real-world schemata and scene recognition in adults and children. Mem. Cogn. 6(4), 423\u2013431 (1978)","journal-title":"Mem. Cogn."},{"issue":"1","key":"36_CR28","doi-asserted-by":"publisher","first-page":"151","DOI":"10.1007\/s11263-006-0031-y","volume":"75","author":"D Hoiem","year":"2007","unstructured":"Hoiem, D., Efros, A.A., Hebert, M.: Recovering surface layout from an image. IJCV 75(1), 151\u2013172 (2007)","journal-title":"IJCV"},{"key":"36_CR29","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":"36_CR30","doi-asserted-by":"crossref","unstructured":"Isola, P., Liu, C.: Scene collaging: analysis and synthesis of natural images with semantic layers. In: ICCV (2013)","DOI":"10.1109\/ICCV.2013.457"},{"key":"36_CR31","doi-asserted-by":"crossref","unstructured":"Isola, P., Zhu, J.Y., Zhou, T., Efros, A.A.: Image-to-image translation with conditional adversarial networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1125\u20131134 (2017)","DOI":"10.1109\/CVPR.2017.632"},{"key":"36_CR32","unstructured":"Jahanian, A., Chai, L., Isola, P.: On the \u201csteerability\u201d of generative adversarial networks. arXiv preprint arXiv:1907.07171 (2019)"},{"key":"36_CR33","doi-asserted-by":"crossref","unstructured":"Johnson, J., Gupta, A., Fei-Fei, L.: Image generation from scene graphs. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1219\u20131228 (2018)","DOI":"10.1109\/CVPR.2018.00133"},{"key":"36_CR34","doi-asserted-by":"crossref","unstructured":"Johnson, J., Hariharan, B., Van Der Maaten, L., Fei-Fei, L., Lawrence Zitnick, C., Girshick, R.: CLEVR: a diagnostic dataset for compositional language and elementary visual reasoning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2901\u20132910 (2017)","DOI":"10.1109\/CVPR.2017.215"},{"key":"36_CR35","unstructured":"Karras, T., Aila, T., Laine, S., Lehtinen, J.: Progressive growing of GANs for improved quality, stability, and variation (2018)"},{"key":"36_CR36","unstructured":"Karras, T., et al.: Alias-free generative adversarial networks. Adv. Neural Inf. Process. Syst. 34 (2021)"},{"key":"36_CR37","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., Aila, T.: A style-based generator architecture for generative adversarial networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4401\u20134410 (2019)","DOI":"10.1109\/CVPR.2019.00453"},{"key":"36_CR38","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., Aittala, M., Hellsten, J., Lehtinen, J., Aila, T.: Analyzing and improving the image quality of StyleGAN. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8110\u20138119 (2020)","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"36_CR39","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., Aittala, M., Hellsten, J., Lehtinen, J., Aila, T.: Analyzing and improving the image quality of StyleGAN (2020)","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"36_CR40","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"36_CR41","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114 (2013)"},{"key":"36_CR42","unstructured":"Kynk\u00e4\u00e4nniemi, T., Karras, T., Laine, S., Lehtinen, J., Aila, T.: Improved precision and recall metric for assessing generative models. Adv. Neural Inf. Process. Syst. 32 (2019)"},{"key":"36_CR43","doi-asserted-by":"crossref","unstructured":"Lewis, K.M., Varadharajan, S., Kemelmacher-Shlizerman, I.: TryonGAN: body-aware try-on via layered interpolation. ACM Trans. Graph. (Proc. ACM SIGGRAPH 2021) 40(4), 1\u201310 (2021)","DOI":"10.1145\/3476576.3476682"},{"key":"36_CR44","doi-asserted-by":"crossref","unstructured":"Li, K., Zhang, T., Malik, J.: Diverse image synthesis from semantic layouts via conditional IMLE. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4220\u20134229 (2019)","DOI":"10.1109\/ICCV.2019.00432"},{"key":"36_CR45","doi-asserted-by":"crossref","unstructured":"Li, Y., Li, Y., Lu, J., Shechtman, E., Lee, Y.J., Singh, K.K.: Collaging class-specific GANs for semantic image synthesis. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 14418\u201314427 (2021)","DOI":"10.1109\/ICCV48922.2021.01415"},{"key":"36_CR46","unstructured":"Locatello, F., et al.: Challenging common assumptions in the unsupervised learning of disentangled representations. In: International Conference on Machine Learning, pp. 4114\u20134124. PMLR (2019)"},{"key":"36_CR47","unstructured":"Malisiewicz, T., Efros, A.: Beyond categories: the visual memex model for reasoning about object relationships. Adv. Neural Inf. Process. Syst. 22 (2009)"},{"key":"36_CR48","unstructured":"Mejjati, Y.A., Milefchik, I., Gokaslan, A., Wang, O., Kim, K.I., Tompkin, J.: GaussiGAN: controllable image synthesis with 3D gaussians from unposed silhouettes. arXiv preprint arXiv:2106.13215 (2021)"},{"key":"36_CR49","unstructured":"Mejjati, Y.A., et al.: Generating object stamps. In: Computer Vision and Pattern Recognition Workshop on AI for Content Creation (CVPRW) (2020)"},{"key":"36_CR50","unstructured":"Meng, C., Song, Y., Song, J., Wu, J., Zhu, J.Y., Ermon, S.: SDEdit: image synthesis and editing with stochastic differential equations. arXiv preprint arXiv:2108.01073 (2021)"},{"key":"36_CR51","doi-asserted-by":"crossref","unstructured":"Nguyen-Phuoc, T., Li, C., Theis, L., Richardt, C., Yang, Y.L.: HoloGAN: unsupervised learning of 3D representations from natural images. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7588\u20137597 (2019)","DOI":"10.1109\/ICCV.2019.00768"},{"key":"36_CR52","first-page":"6767","volume":"33","author":"TH Nguyen-Phuoc","year":"2020","unstructured":"Nguyen-Phuoc, T.H., Richardt, C., Mai, L., Yang, Y., Mitra, N.: BlockGAN: learning 3D object-aware scene representations from unlabelled images. Adv. Neural. Inf. Process. Syst. 33, 6767\u20136778 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"36_CR53","unstructured":"Nichol, A., et al.: GLIDE: towards photorealistic image generation and editing with text-guided diffusion models. arXiv preprint arXiv:2112.10741 (2021)"},{"key":"36_CR54","doi-asserted-by":"crossref","unstructured":"Niemeyer, M., Geiger, A.: GIRAFFE: representing scenes as compositional generative neural feature fields. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2021)","DOI":"10.1109\/CVPR46437.2021.01129"},{"key":"36_CR55","unstructured":"Nitzberg, M., Mumford, D.B.: The 2.1-D Sketch. IEEE Computer Society Press (1990)"},{"key":"36_CR56","unstructured":"Ohta, Y., Kanade, T., Sakai, T.: An analysis system for scenes containing objects with substructures. In: Proceedings of 4th International Joint Conference on Pattern Recognition (IJCPR 1978), pp. 752\u2013754 (1978)"},{"key":"36_CR57","unstructured":"Oktay, D., Vondrick, C., Torralba, A.: Counterfactual image networks (2018). https:\/\/openreview.net\/forum?id=SyYYPdg0-"},{"issue":"12","key":"36_CR58","doi-asserted-by":"publisher","first-page":"520","DOI":"10.1016\/j.tics.2007.09.009","volume":"11","author":"A Oliva","year":"2007","unstructured":"Oliva, A., Torralba, A.: The role of context in object recognition. Trends Cogn. Sci. 11(12), 520\u2013527 (2007)","journal-title":"Trends Cogn. Sci."},{"key":"36_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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2337\u20132346 (2019)","DOI":"10.1109\/CVPR.2019.00244"},{"key":"36_CR60","first-page":"7198","volume":"33","author":"T Park","year":"2020","unstructured":"Park, T., et al.: Swapping autoencoder for deep image manipulation. Adv. Neural. Inf. Process. Syst. 33, 7198\u20137211 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"36_CR61","doi-asserted-by":"crossref","unstructured":"Patashnik, O., Wu, Z., Shechtman, E., Cohen-Or, D., Lischinski, D.: StyleCLIP: text-driven manipulation of StyleGAN imagery. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2085\u20132094 (2021)","DOI":"10.1109\/ICCV48922.2021.00209"},{"key":"36_CR62","doi-asserted-by":"crossref","unstructured":"Pathak, D., Kr\u00e4henb\u00fchl, P., Donahue, J., Darrell, T., Efros, A.: Context encoders: feature learning by inpainting (2016)","DOI":"10.1109\/CVPR.2016.278"},{"key":"36_CR63","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"581","DOI":"10.1007\/978-3-030-58539-6_35","volume-title":"Computer Vision \u2013 ECCV 2020","author":"W Peebles","year":"2020","unstructured":"Peebles, W., Peebles, J., Zhu, J.-Y., Efros, A., Torralba, A.: The hessian penalty: a weak prior for unsupervised disentanglement. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12351, pp. 581\u2013597. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58539-6_35"},{"key":"36_CR64","doi-asserted-by":"crossref","unstructured":"Porter, T., Duff, T.: Compositing digital images. In: Proceedings of the 11th annual Conference on Computer Graphics and Interactive Techniques, pp. 253\u2013259 (1984)","DOI":"10.1145\/800031.808606"},{"key":"36_CR65","unstructured":"Radford, A., Metz, L., Chintala, S.: Unsupervised representation learning with deep convolutional generative adversarial networks. arXiv preprint arXiv:1511.06434 (2015)"},{"key":"36_CR66","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., Chen, M.: Hierarchical text-conditional image generation with clip latents. arXiv preprint arXiv:2204.06125 (2022)"},{"key":"36_CR67","unstructured":"Ramesh, A., et al.: Zero-shot text-to-image generation. In: International Conference on Machine Learning, pp. 8821\u20138831. PMLR (2021)"},{"key":"36_CR68","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, pp. 1060\u20131069. PMLR (2016)"},{"key":"36_CR69","doi-asserted-by":"crossref","unstructured":"Richardson, E., et al.: Encoding in style: a StyleGAN encoder for image-to-image translation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2287\u20132296 (2021)","DOI":"10.1109\/CVPR46437.2021.00232"},{"key":"36_CR70","doi-asserted-by":"crossref","unstructured":"Roich, D., Mokady, R., Bermano, A.H., Cohen-Or, D.: Pivotal tuning for latent-based editing of real images. arXiv preprint arXiv:2106.05744 (2021)","DOI":"10.1145\/3544777"},{"key":"36_CR71","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. arXiv preprint arXiv:2112.10752 (2021)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"36_CR72","doi-asserted-by":"crossref","unstructured":"Rott Shaham, T., Dekel, T., Michaeli, T.: SinGAN: learning a generative model from a single natural image. In: IEEE International Conference on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.00467"},{"key":"36_CR73","unstructured":"Russell, B., Efros, A., Sivic, J., Freeman, B., Zisserman, A.: Segmenting scenes by matching image composites. Adv. Neural Inf. Process. Syst. 22 (2009)"},{"key":"36_CR74","doi-asserted-by":"crossref","unstructured":"Saharia, C., et al.: Palette: Image-to-image diffusion models. arXiv preprint arXiv:2111.05826 (2021)","DOI":"10.1145\/3528233.3530757"},{"key":"36_CR75","unstructured":"Sarkar, K., Golyanik, V., Liu, L., Theobalt, C.: Style and pose control for image synthesis of humans from a single monocular view (2021)"},{"key":"36_CR76","unstructured":"Shen, Y., Yang, C., Tang, X., Zhou, B.: InterFaceGAN: interpreting the disentangled face representation learned by GANs. IEEE Trans. Pattern Anal. Mach. Intell. (2020)"},{"key":"36_CR77","doi-asserted-by":"crossref","unstructured":"Shen, Y., Zhou, B.: Closed-form factorization of latent semantics in GANs. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1532\u20131540 (2021)","DOI":"10.1109\/CVPR46437.2021.00158"},{"issue":"8","key":"36_CR78","doi-asserted-by":"publisher","first-page":"888","DOI":"10.1109\/34.868688","volume":"22","author":"J Shi","year":"2000","unstructured":"Shi, J., Malik, J.: Normalized cuts and image segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 22(8), 888\u2013905 (2000)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"36_CR79","unstructured":"Siarohin, A., Lathuili\u00e8re, S., Tulyakov, S., Ricci, E., Sebe, N.: First order motion model for image animation. In: Conference on Neural Information Processing Systems (NeurIPS) (2019)"},{"key":"36_CR80","doi-asserted-by":"crossref","unstructured":"Siarohin, A., Woodford, O., Ren, J., Chai, M., Tulyakov, S.: Motion representations for articulated animation. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01344"},{"key":"36_CR81","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":"36_CR82","doi-asserted-by":"crossref","unstructured":"Simakov, D., Caspi, Y., Shechtman, E., Irani, M.: Summarizing visual data using bidirectional similarity. In: CVPR. IEEE Computer Society (2008)","DOI":"10.1109\/CVPR.2008.4587842"},{"key":"36_CR83","doi-asserted-by":"crossref","unstructured":"Strudel, R., Garcia, R., Laptev, I., Schmid, C.: Segmenter: transformer for semantic segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7262\u20137272 (2021)","DOI":"10.1109\/ICCV48922.2021.00717"},{"key":"36_CR84","doi-asserted-by":"crossref","unstructured":"Sudderth, E.B., Torralba, A., Freeman, W.T., Willsky, A.S.: Learning hierarchical models of scenes, objects, and parts. In: Tenth IEEE International Conference on Computer Vision (ICCV 2005) Volume 1, vol. 2, pp. 1331\u20131338. IEEE (2005)","DOI":"10.1109\/ICCV.2005.137"},{"key":"36_CR85","unstructured":"Torralba, A., Willsky, A., Sudderth, E., Freeman, W.: Describing visual scenes using transformed Dirichlet processes. Adv. Neural Inf. Process. Syst. 18 (2005)"},{"issue":"4","key":"36_CR86","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3450626.3459838","volume":"40","author":"O Tov","year":"2021","unstructured":"Tov, O., Alaluf, Y., Nitzan, Y., Patashnik, O., Cohen-Or, D.: Designing an encoder for StyleGAN image manipulation. ACM Trans. Graph. (TOG) 40(4), 1\u201314 (2021)","journal-title":"ACM Trans. Graph. (TOG)"},{"issue":"2","key":"36_CR87","doi-asserted-by":"publisher","first-page":"113","DOI":"10.1007\/s11263-005-6642-x","volume":"63","author":"Z Tu","year":"2005","unstructured":"Tu, Z., Chen, X., Yuille, A.L., Zhu, S.C.: Image parsing: unifying segmentation, detection, and recognition. Int. J. Comput. Vis. 63(2), 113\u2013140 (2005)","journal-title":"Int. J. Comput. Vis."},{"key":"36_CR88","doi-asserted-by":"crossref","unstructured":"Wang, J., Yang, C., Xu, Y., Shen, Y., Li, H., Zhou, B.: Improving GAN equilibrium by raising spatial awareness. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11285\u201311293 (2022)","DOI":"10.1109\/CVPR52688.2022.01100"},{"key":"36_CR89","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: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8798\u20138807 (2018)","DOI":"10.1109\/CVPR.2018.00917"},{"key":"36_CR90","doi-asserted-by":"crossref","unstructured":"Wu, Z., Lischinski, D., Shechtman, E.: StyleSpace analysis: disentangled controls for StyleGAN image generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12863\u201312872 (2021)","DOI":"10.1109\/CVPR46437.2021.01267"},{"key":"36_CR91","unstructured":"Yakimovsky, Y., Feldman, J.A.: A semantics-based decision theory region analyser. In: IJCAI, pp. 580\u2013588. William Kaufmann (1973)"},{"issue":"5","key":"36_CR92","doi-asserted-by":"publisher","first-page":"1451","DOI":"10.1007\/s11263-020-01429-5","volume":"129","author":"C Yang","year":"2021","unstructured":"Yang, C., Shen, Y., Zhou, B.: Semantic hierarchy emerges in deep generative representations for scene synthesis. Int. J. Comput. Vis. 129(5), 1451\u20131466 (2021)","journal-title":"Int. J. Comput. Vis."},{"key":"36_CR93","unstructured":"Yao, S., et al.: 3D-aware scene manipulation via inverse graphics. Adv. Neural Inf. Process. Syst. 31 (2018)"},{"key":"36_CR94","unstructured":"Yu, F., Seff, A., Zhang, Y., Song, S., Funkhouser, T., Xiao, J.: LSUN: construction of a large-scale image dataset using deep learning with humans in the loop. arXiv preprint arXiv:1506.03365 (2015)"},{"key":"36_CR95","unstructured":"Yu, H.X., Guibas, L.J., Wu, J.: Unsupervised discovery of object radiance fields. arXiv preprint arXiv:2107.07905 (2021)"},{"key":"36_CR96","unstructured":"Yu, S.X., Gross, R., Shi, J.: Concurrent object recognition and segmentation by graph partitioning. Adv. Neural Inf. Process. Syst. 15 (2002)"},{"key":"36_CR97","unstructured":"Zhang, C., Xu, Y., Shen, Y.: Decorating your own bedroom: locally controlling image generation with generative adversarial networks. arXiv preprint arXiv:2105.08222 (2021)"},{"key":"36_CR98","unstructured":"Zhang, H., Goodfellow, I., Metaxas, D., Odena, A.: Self-attention generative adversarial networks. In: International conference on machine learning, pp. 7354\u20137363. PMLR (2019)"},{"key":"36_CR99","doi-asserted-by":"crossref","unstructured":"Zhang, H., et al.: StackGAN: text to photo-realistic image synthesis with stacked generative adversarial networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 5907\u20135915 (2017)","DOI":"10.1109\/ICCV.2017.629"},{"key":"36_CR100","doi-asserted-by":"crossref","unstructured":"Zhang, R., Isola, P., Efros, A.A., Shechtman, E., Wang, O.: The unreasonable effectiveness of deep features as a perceptual metric. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 586\u2013595 (2018)","DOI":"10.1109\/CVPR.2018.00068"},{"key":"36_CR101","unstructured":"Zhu, J., Shen, Y., Xu, Y., Zhao, D., Chen, Q.: Region-based semantic factorization in GANs. arXiv preprint arXiv:2202.09649 (2022)"},{"key":"36_CR102","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"597","DOI":"10.1007\/978-3-319-46454-1_36","volume-title":"Computer Vision \u2013 ECCV 2016","author":"J-Y Zhu","year":"2016","unstructured":"Zhu, J.-Y., Kr\u00e4henb\u00fchl, P., Shechtman, E., Efros, A.A.: Generative visual manipulation on the natural image manifold. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9909, pp. 597\u2013613. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46454-1_36"},{"key":"36_CR103","unstructured":"Zhu, J.Y., et al.: Toward multimodal image-to-image translation. Adv. Neural Inf. Process. Syst. 30 (2017)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-19784-0_36","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T19:42:19Z","timestamp":1710358939000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-19784-0_36"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031197833","9783031197840"],"references-count":103,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-19784-0_36","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"31 October 2022","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":"Tel Aviv","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Israel","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2022.ecva.net\/","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":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5804","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":"1645","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":"28% - 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":"3.21","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":"3.91","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)"}}]}}