{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:44:16Z","timestamp":1778082256289,"version":"3.51.4"},"publisher-location":"Cham","reference-count":62,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031729850","type":"print"},{"value":"9783031729867","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T00:00:00Z","timestamp":1730505600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T00:00:00Z","timestamp":1730505600000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-72986-7_14","type":"book-chapter","created":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T05:04:43Z","timestamp":1730437483000},"page":"234-251","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Merging and\u00a0Splitting Diffusion Paths for\u00a0Semantically Coherent Panoramas"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-3244-6186","authenticated-orcid":false,"given":"Fabio","family":"Quattrini","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-7365-6348","authenticated-orcid":false,"given":"Vittorio","family":"Pippi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7885-6050","authenticated-orcid":false,"given":"Silvia","family":"Cascianelli","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2239-283X","authenticated-orcid":false,"given":"Rita","family":"Cucchiara","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,11,2]]},"reference":[{"issue":"4","key":"14_CR1","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3592450","volume":"42","author":"O Avrahami","year":"2023","unstructured":"Avrahami, O., Fried, O., Lischinski, D.: Blended latent diffusion. ACM Trans. Graphics 42(4), 1\u201311 (2023)","journal-title":"ACM Trans. Graphics"},{"key":"14_CR2","doi-asserted-by":"crossref","unstructured":"Avrahami, O., et al.: SpaText: spatio-textual representation for controllable image generation. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01762"},{"key":"14_CR3","doi-asserted-by":"crossref","unstructured":"Avrahami, O., Lischinski, D., Fried, O.: Blended diffusion for text-driven editing of natural images. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01767"},{"key":"14_CR4","unstructured":"Balaji, Y., et\u00a0al.: eDiff-I: text-to-image diffusion models with an ensemble of expert denoisers. arXiv preprint arXiv:2211.01324 (2022)"},{"key":"14_CR5","unstructured":"Bar-Tal, O., Yariv, L., Lipman, Y., Dekel, T.: MultiDiffusion: fusing diffusion paths for controlled image generation. In: ICML (2023)"},{"key":"14_CR6","unstructured":"Bi\u0144kowski, M., Sutherland, D.J., Arbel, M., Gretton, A.: Demystifying MMD GANs. In: ICLR (2018)"},{"key":"14_CR7","unstructured":"Brock, A., Donahue, J., Simonyan, K.: Large scale GAN training for high fidelity natural image synthesis. In: ICLR (2018)"},{"key":"14_CR8","doi-asserted-by":"crossref","unstructured":"Brooks, T., Holynski, A., Efros, A.A.: InstructPix2Pix: learning to follow image editing instructions. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"14_CR9","doi-asserted-by":"crossref","unstructured":"Chen, J., et al.: PixArt-$$\\alpha $$: fast training of diffusion transformer for photorealistic text-to-image synthesis. In: ICLR (2024)","DOI":"10.1007\/978-3-031-73411-3_5"},{"key":"14_CR10","unstructured":"Chen, N., Zhang, Y., Zen, H., Weiss, R.J., Norouzi, M., Chan, W.: WaveGrad: estimating gradients for waveform generation. In: ICLR (2020)"},{"key":"14_CR11","unstructured":"Couairon, G., Verbeek, J., Schwenk, H., Cord, M.: DiffEdit: diffusion-based semantic image editing with mask guidance. In: ICLR (2022)"},{"key":"14_CR12","unstructured":"Dhariwal, P., Nichol, A.: Diffusion models beat GANs on image synthesis. In: NeurIPS (2021)"},{"key":"14_CR13","doi-asserted-by":"crossref","unstructured":"Esser, P., Chiu, J., Atighehchian, P., Granskog, J., Germanidis, A.: Structure and content-guided video synthesis with diffusion models. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00675"},{"key":"14_CR14","doi-asserted-by":"crossref","unstructured":"Esser, P., Rombach, R., Ommer, B.: Taming transformers for high-resolution image synthesis. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"14_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1007\/978-3-031-19784-0_6","volume-title":"Computer Vision \u2013 ECCV 2022","author":"O Gafni","year":"2022","unstructured":"Gafni, O., Polyak, A., Ashual, O., Sheynin, S., Parikh, D., Taigman, Y.: Make-a-scene: scene-based text-to-image generation with human priors. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13675, pp. 89\u2013106. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19784-0_6"},{"key":"14_CR16","doi-asserted-by":"crossref","unstructured":"Gatys, L.A., Ecker, A.S., Bethge, M.: Image style transfer using convolutional neural networks. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.265"},{"key":"14_CR17","unstructured":"Goodfellow, I., et al.: Generative adversarial nets. In: NeurIPS (2014)"},{"key":"14_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"369","DOI":"10.1007\/978-3-030-58621-8_22","volume-title":"Computer Vision \u2013 ECCV 2020","author":"S Gu","year":"2020","unstructured":"Gu, S., Bao, J., Chen, D., Wen, F.: GIQA: generated image quality assessment. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12356, pp. 369\u2013385. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58621-8_22"},{"key":"14_CR19","unstructured":"He, Y., et al.: ScaleCrafter: tuning-free higher-resolution visual generation with diffusion models. In: ICLR (2024)"},{"key":"14_CR20","unstructured":"Hertz, A., Mokady, R., Tenenbaum, J., Aberman, K., Pritch, Y., Cohen-or, D.: Prompt-to-prompt image editing with cross-attention control. In: ICLR (2022)"},{"key":"14_CR21","doi-asserted-by":"crossref","unstructured":"Hessel, J., Holtzman, A., Forbes, M., Le\u00a0Bras, R., Choi, Y.: CLIPScore: a reference-free evaluation metric for image captioning. In: EMNLP (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"14_CR22","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. NeurIPS (2017)"},{"key":"14_CR23","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. In: NeurIPS (2020)"},{"key":"14_CR24","unstructured":"Ho, J., Salimans, T.: Classifier-free diffusion guidance. In: NeurIPS Workshop (2021)"},{"key":"14_CR25","unstructured":"Ho, J., Salimans, T., Gritsenko, A.A., Chan, W., Norouzi, M., Fleet, D.J.: Video diffusion models. In: ICLR Workshop (2022)"},{"key":"14_CR26","unstructured":"Jin, Z., Shen, X., Li, B., Xue, X.: Training-free diffusion model adaptation for variable-sized text-to-image synthesis. In: NeurIPS (2023)"},{"key":"14_CR27","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: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"14_CR28","doi-asserted-by":"crossref","unstructured":"Khachatryan, L., et al.: Text2Video-zero: text-to-image diffusion models are zero-shot video generators. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.01462"},{"key":"14_CR29","unstructured":"Kong, Z., Ping, W., Huang, J., Zhao, K., Catanzaro, B.: DiffWave: a versatile diffusion model for audio synthesis. In: ICLR (2021)"},{"key":"14_CR30","unstructured":"Lee, Y., Kim, K., Kim, H., Sung, M.: SyncDiffusion: coherent montage via synchronized joint diffusions. In: NeurIPS (2023)"},{"key":"14_CR31","doi-asserted-by":"crossref","unstructured":"Lin, C.H., et al.: Magic3D: high-resolution text-to-3D content creation. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00037"},{"issue":"3","key":"14_CR32","doi-asserted-by":"publisher","first-page":"243","DOI":"10.1038\/s41592-018-0308-4","volume":"16","author":"GC Linderman","year":"2019","unstructured":"Linderman, G.C., Rachh, M., Hoskins, J.G., Steinerberger, S., Kluger, Y.: Fast interpolation-based t-SNE for improved visualization of single-cell RNA-seq data. Nat. Methods 16(3), 243\u2013245 (2019)","journal-title":"Nat. Methods"},{"key":"14_CR33","doi-asserted-by":"crossref","unstructured":"Lugmayr, A., Danelljan, M., Romero, A., Yu, F., Timofte, R., Van\u00a0Gool, L.: RePaint: inpainting using denoising diffusion probabilistic models. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01117"},{"key":"14_CR34","unstructured":"Luo, S., Tan, Y., Huang, L., Li, J., Zhao, H.: Latent consistency models: synthesizing high-resolution images with few-step inference (2023)"},{"key":"14_CR35","unstructured":"Van\u00a0der Maaten, L., Hinton, G.: Visualizing data using t-SNE. J. Mach. Learn. Res. 9(11) (2008)"},{"key":"14_CR36","unstructured":"Meng, C., et al.: SDEdit: guided image synthesis and editing with stochastic differential equations. In: ICLR (2022)"},{"key":"14_CR37","doi-asserted-by":"crossref","unstructured":"Mokady, R., Hertz, A., Aberman, K., Pritch, Y., Cohen-Or, D.: Null-text inversion for editing real images using guided diffusion models. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00585"},{"key":"14_CR38","unstructured":"Nichol, A.Q., Dhariwal, P.: Improved denoising diffusion probabilistic models. In: ICML (2021)"},{"key":"14_CR39","doi-asserted-by":"crossref","unstructured":"Peebles, W., Xie, S.: Scalable diffusion models with transformers. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"14_CR40","unstructured":"Podell, D., et al.: SDXL: improving latent diffusion models for high-resolution image synthesis. In: ICLR (2024)"},{"key":"14_CR41","doi-asserted-by":"crossref","unstructured":"Poli\u010dar, P.G., Stra\u017ear, M., Zupan, B.: openTSNE: a modular Python library for t-SNE dimensionality reduction and embedding. BioRxiv (2019)","DOI":"10.1101\/731877"},{"key":"14_CR42","unstructured":"Popov, V., Vovk, I., Gogoryan, V., Sadekova, T., Kudinov, M.: Grad-TTS: a diffusion probabilistic model for text-to-speech. In: ICML (2021)"},{"key":"14_CR43","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: ICML (2021)"},{"key":"14_CR44","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., Chen, M.: Hierarchical text-conditional image generation with CLIP latents. arXiv e-prints, pp. arXiv\u20132204 (2022)"},{"key":"14_CR45","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"14_CR46","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1007\/978-3-319-24574-4_28","volume-title":"Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI 2015","author":"O Ronneberger","year":"2015","unstructured":"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\u2013241. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28"},{"issue":"4","key":"14_CR47","first-page":"4713","volume":"45","author":"C Saharia","year":"2022","unstructured":"Saharia, C., Ho, J., Chan, W., Salimans, T., Fleet, D.J., Norouzi, M.: Image super-resolution via iterative refinement. IEEE Trans. PAMI 45(4), 4713\u20134726 (2022)","journal-title":"IEEE Trans. PAMI"},{"key":"14_CR48","unstructured":"Sohl-Dickstein, J., Weiss, E., Maheswaranathan, N., Ganguli, S.: Deep unsupervised learning using nonequilibrium thermodynamics. In: ICML (2015)"},{"key":"14_CR49","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. In: ICLR (2021)"},{"key":"14_CR50","unstructured":"Song, Y., Dhariwal, P., Chen, M., Sutskever, I.: Consistency models. In: ICML (2023)"},{"key":"14_CR51","unstructured":"Song, Y., Ermon, S.: Generative modeling by estimating gradients of the data distribution. In: NeurIPS (2019)"},{"key":"14_CR52","unstructured":"Song, Y., Ermon, S.: Improved techniques for training score-based generative models. In: NeurIPS (2020)"},{"key":"14_CR53","unstructured":"Song, Y., Sohl-Dickstein, J., Kingma, D.P., Kumar, A., Ermon, S., Poole, B.: Score-based generative modeling through stochastic differential equations. In: ICLR (2021)"},{"key":"14_CR54","doi-asserted-by":"crossref","unstructured":"Tumanyan, N., Geyer, M., Bagon, S., Dekel, T.: Plug-and-play diffusion features for text-driven image-to-image translation. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00191"},{"key":"14_CR55","unstructured":"Van Den\u00a0Oord, A., Vinyals, O., et\u00a0al.: Neural discrete representation learning. In: NeurIPS (2017)"},{"key":"14_CR56","unstructured":"Von\u00a0Platen, P., et al.: Diffusers: state-of-the-art diffusion models (2022). https:\/\/github.com\/huggingface\/diffusers"},{"key":"14_CR57","unstructured":"Wang, W., et al.: Zero-shot video editing using off-the-shelf image diffusion models. arXiv preprint arXiv:2303.17599 (2023)"},{"key":"14_CR58","doi-asserted-by":"crossref","unstructured":"Wu, J.Z., et al.: Tune-a-video: one-shot tuning of image diffusion models for text-to-video generation. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00701"},{"key":"14_CR59","doi-asserted-by":"crossref","unstructured":"Xu, J., et al.: Dream3D: zero-shot text-to-3D synthesis using 3D shape prior and text-to-image diffusion models. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.02003"},{"key":"14_CR60","doi-asserted-by":"crossref","unstructured":"Zhang, L., Rao, A., Agrawala, M.: Adding conditional control to text-to-image diffusion models. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"14_CR61","doi-asserted-by":"crossref","unstructured":"Zhang, Q., Song, J., Huang, X., Chen, Y., Liu, M.Y.: DiffCollage: parallel generation of large content with diffusion models. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00982"},{"key":"14_CR62","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: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00068"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72986-7_14","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,30]],"date-time":"2024-11-30T16:45:47Z","timestamp":1732985147000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72986-7_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,2]]},"ISBN":["9783031729850","9783031729867"],"references-count":62,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72986-7_14","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,2]]},"assertion":[{"value":"2 November 2024","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":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}