{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:05:59Z","timestamp":1777655159810,"version":"3.51.4"},"publisher-location":"Cham","reference-count":58,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031731129","type":"print"},{"value":"9783031731136","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,21]],"date-time":"2024-11-21T00:00:00Z","timestamp":1732147200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,21]],"date-time":"2024-11-21T00:00:00Z","timestamp":1732147200000},"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\/978-3-031-73113-6_17","type":"book-chapter","created":{"date-parts":[[2024,11,20]],"date-time":"2024-11-20T08:49:30Z","timestamp":1732092570000},"page":"289-305","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Scene-Conditional 3D Object Stylization and\u00a0Composition"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-6904-3328","authenticated-orcid":false,"given":"Jinghao","family":"Zhou","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-5911-9569","authenticated-orcid":false,"given":"Tomas","family":"Jakab","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-0259-5732","authenticated-orcid":false,"given":"Philip","family":"Torr","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3994-8045","authenticated-orcid":false,"given":"Christian","family":"Rupprecht","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,11,21]]},"reference":[{"key":"17_CR1","unstructured":"https:\/\/polyhaven.com"},{"key":"17_CR2","doi-asserted-by":"crossref","unstructured":"Akimoto, N., Matsuo, Y., Aoki, Y.: Diverse plausible 360-degree image outpainting for efficient 3DCG background creation. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01115"},{"key":"17_CR3","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":"17_CR4","doi-asserted-by":"crossref","unstructured":"Cao, T., Kreis, K., Fidler, S., Sharp, N., Yin, K.: TexFusion: synthesizing 3D textures with text-guided image diffusion models. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00385"},{"key":"17_CR5","doi-asserted-by":"crossref","unstructured":"Chen, B.C., Kae, A.: Toward realistic image compositing with adversarial learning. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00861"},{"key":"17_CR6","doi-asserted-by":"crossref","unstructured":"Chen, D.Z., Siddiqui, Y., Lee, H.Y., Tulyakov, S., Nie\u00dfner, M.: Text2Tex: text-driven texture synthesis via diffusion models. arXiv preprint arXiv:2303.11396 (2023)","DOI":"10.1109\/ICCV51070.2023.01701"},{"key":"17_CR7","doi-asserted-by":"crossref","unstructured":"Chen, R., Chen, Y., Jiao, N., Jia, K.: Fantasia3D: disentangling geometry and appearance for high-quality text-to-3D content creation. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.02033"},{"key":"17_CR8","doi-asserted-by":"crossref","unstructured":"Cong, W., Niu, L., Zhang, J., Liang, J., Zhang, L.: BargainNet: background-guided domain translation for image harmonization. In: ICME (2021)","DOI":"10.1109\/ICME51207.2021.9428394"},{"key":"17_CR9","doi-asserted-by":"crossref","unstructured":"Cong, W., et al.: DoveNet: deep image harmonization via domain verification. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00842"},{"key":"17_CR10","doi-asserted-by":"crossref","unstructured":"Deitke, M., et al.: Objaverse: a universe of annotated 3D objects. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"17_CR11","unstructured":"Deng, Y., Li, X., Liu, S., Yang, M.H.: DIP: differentiable interreflection-aware physics-based inverse rendering. arXiv preprint arXiv:2212.04705 (2022)"},{"key":"17_CR12","unstructured":"Dhariwal, P., Nichol, A.: Diffusion models beat GANs on image synthesis. In: NeurIPS (2021)"},{"key":"17_CR13","doi-asserted-by":"crossref","unstructured":"Eftekhar, A., Sax, A., Malik, J., Zamir, A.: Omnidata: a scalable pipeline for making multi-task mid-level vision datasets from 3D scans. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01061"},{"key":"17_CR14","unstructured":"Gao, J., et al.: Get3D: a generative model of high quality 3D textured shapes learned from images. In: NeurIPS (2022)"},{"key":"17_CR15","doi-asserted-by":"crossref","unstructured":"Gardner, M.A., Hold-Geoffroy, Y., Sunkavalli, K., Gagn\u00e9, C., Lalonde, J.F.: Deep parametric indoor lighting estimation. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00727"},{"key":"17_CR16","doi-asserted-by":"crossref","unstructured":"Gardner, M.A., et al.: Learning to predict indoor illumination from a single image. arXiv preprint arXiv:1704.00090 (2017)","DOI":"10.1145\/3130800.3130891"},{"key":"17_CR17","unstructured":"Goodfellow, I., et al.: Generative adversarial nets. In: NeurIPS (2014)"},{"key":"17_CR18","unstructured":"Hachnochi, R., et al.: Cross-domain compositing with pretrained diffusion models. arXiv preprint arXiv:2302.10167 (2023)"},{"key":"17_CR19","doi-asserted-by":"crossref","unstructured":"Haque, A., Tancik, M., Efros, A., Holynski, A., Kanazawa, A.: Instruct-NeRF2NeRF: editing 3D scenes with instructions. In: CVPR (2023)","DOI":"10.1109\/ICCV51070.2023.01808"},{"key":"17_CR20","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. In: NeurIPS (2020)"},{"key":"17_CR21","unstructured":"Ho, J., Salimans, T.: Classifier-free diffusion guidance. In: NeurIPSW (2021)"},{"key":"17_CR22","doi-asserted-by":"crossref","unstructured":"Hold-Geoffroy, Y., Athawale, A., Lalonde, J.F.: Deep sky modeling for single image outdoor lighting estimation. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00709"},{"key":"17_CR23","doi-asserted-by":"crossref","unstructured":"Hold-Geoffroy, Y., Sunkavalli, K., Hadap, S., Gambaretto, E., Lalonde, J.F.: Deep outdoor illumination estimation. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.255"},{"key":"17_CR24","doi-asserted-by":"crossref","unstructured":"Jakob, W., Speierer, S., Roussel, N., Vicini, D.: Dr.Jit: a just-in-time compiler for differentiable rendering. TOG 41, 1\u201319 (2022)","DOI":"10.1145\/3528223.3530099"},{"key":"17_CR25","doi-asserted-by":"crossref","unstructured":"Jiang, Y., et al.: SSH: a self-supervised framework for image harmonization. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00479"},{"key":"17_CR26","unstructured":"Kamata, H., Sakuma, Y., Hayakawa, A., Ishii, M., Narihira, T.: Instruct 3D-to-3D: text instruction guided 3D-to-3D conversion. arXiv preprint arXiv:2303.15780 (2023)"},{"key":"17_CR27","doi-asserted-by":"crossref","unstructured":"Karimi\u00a0Dastjerdi, M.R., Eisenmann, J., Hold-Geoffroy, Y., Lalonde, J.F.: EverLight: indoor-outdoor editable HDR lighting estimation. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00682"},{"key":"17_CR28","doi-asserted-by":"crossref","unstructured":"Karimi\u00a0Dastjerdi, M.R., Hold-Geoffroy, Y., Eisenmann, J., Khodadadeh, S., Lalonde, J.F.: Guided co-modulated GAN for 360 field of view extrapolation. In: 3DV (2022)","DOI":"10.1109\/3DV57658.2022.00059"},{"key":"17_CR29","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"},{"key":"17_CR30","unstructured":"Liu, M., et\u00a0al.: One-2-3-45: any single image to 3D mesh in 45 seconds without per-shape optimization. arXiv preprint arXiv:2306.16928 (2023)"},{"key":"17_CR31","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":"17_CR32","doi-asserted-by":"crossref","unstructured":"McAuley, S., et al.: Practical physically-based shading in film and game production. In: SIGGRAPH (2012)","DOI":"10.1145\/2343483.2343493"},{"key":"17_CR33","doi-asserted-by":"crossref","unstructured":"Metzer, G., Richardson, E., Patashnik, O., Giryes, R., Cohen-Or, D.: Latent-NeRF for shape-guided generation of 3D shapes and textures. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01218"},{"key":"17_CR34","doi-asserted-by":"crossref","unstructured":"Michel, O., Bar-On, R., Liu, R., Benaim, S., Hanocka, R.: Text2Mesh: text-driven neural stylization for meshes (2022)","DOI":"10.1109\/CVPR52688.2022.01313"},{"key":"17_CR35","doi-asserted-by":"crossref","unstructured":"Mohammad\u00a0Khalid, N., Xie, T., Belilovsky, E., Popa, T.: CLIP-Mesh: generating textured meshes from text using pretrained image-text models. In: SIGGRAPH Asia (2022)","DOI":"10.1145\/3550469.3555392"},{"key":"17_CR36","doi-asserted-by":"crossref","unstructured":"Munkberg, J., et al.: Extracting triangular 3D models, materials, and lighting from images. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00810"},{"key":"17_CR37","doi-asserted-by":"crossref","unstructured":"Oechsle, M., Mescheder, L., Niemeyer, M., Strauss, T., Geiger, A.: Texture fields: learning texture representations in function space. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00463"},{"key":"17_CR38","unstructured":"OpenAI: GPT-4 technical report (2023)"},{"key":"17_CR39","doi-asserted-by":"crossref","unstructured":"Parmar, G., Kumar\u00a0Singh, K., Zhang, R., Li, Y., Lu, J., Zhu, J.Y.: Zero-shot image-to-image translation. In: SIGGRAPH (2023)","DOI":"10.1145\/3588432.3591513"},{"key":"17_CR40","unstructured":"Poole, B., Jain, A., Barron, J.T., Mildenhall, B.: DreamFusion: text-to-3D using 2D diffusion. In: ICLR (2023)"},{"key":"17_CR41","unstructured":"Qian, G., et al.: Magic123: one image to high-quality 3D object generation using both 2D and 3D diffusion priors. arXiv preprint arXiv:2306.17843 (2023)"},{"key":"17_CR42","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: ICML (2021)"},{"key":"17_CR43","unstructured":"Ramesh, A., et al.: Zero-shot text-to-image generation. In: ICML (2021)"},{"key":"17_CR44","doi-asserted-by":"crossref","unstructured":"Ranftl, R., Lasinger, K., Hafner, D., Schindler, K., Koltun, V.: Towards robust monocular depth estimation: mixing datasets for zero-shot cross-dataset transfer. PAMI (2022)","DOI":"10.1109\/TPAMI.2020.3019967"},{"key":"17_CR45","doi-asserted-by":"crossref","unstructured":"Richardson, E., Metzer, G., Alaluf, Y., Giryes, R., Cohen-Or, D.: Texture: text-guided texturing of 3D shapes. In: SIGGRAPH (2023)","DOI":"10.1145\/3588432.3591503"},{"key":"17_CR46","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models (2021)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"17_CR47","unstructured":"Saharia, C., et\u00a0al.: Photorealistic text-to-image diffusion models with deep language understanding. In: NeurIPS (2022)"},{"key":"17_CR48","doi-asserted-by":"publisher","unstructured":"Siddiqui, Y., Thies, J., Ma, F., Shan, Q., Nie\u00dfner, M., Dai, A.: Texturify: generating textures on 3D shape surfaces. In: Avidan, S., Brostow, G., Cisse, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision \u2013 ECCV 2022. ECCV 2022. LNCS, vol. 13663, pp. 72\u201388. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20062-5_5","DOI":"10.1007\/978-3-031-20062-5_5"},{"key":"17_CR49","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). https:\/\/openreview.net\/forum?id=PxTIG12RRHS"},{"key":"17_CR50","unstructured":"Song, Y., et al.: ObjectStitch: generative object compositing. In: CVPR (2023)"},{"key":"17_CR51","doi-asserted-by":"crossref","unstructured":"Tsalicoglou, C., Manhardt, F., Tonioni, A., Niemeyer, M., Tombari, F.: TextMesh: generation of realistic 3D meshes from text prompts (2024)","DOI":"10.1109\/3DV62453.2024.00154"},{"key":"17_CR52","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":"17_CR53","unstructured":"Walter, B., Marschner, S.R., Li, H., Torrance, K.E.: Microfacet models for refraction through rough surfaces. In: EGSR (2007)"},{"key":"17_CR54","doi-asserted-by":"crossref","unstructured":"Wang, H., Du, X., Li, J., Yeh, R.A., Shakhnarovich, G.: Score Jacobian chaining: lifting pretrained 2D diffusion models for 3D generation. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01214"},{"key":"17_CR55","unstructured":"Wang, Z., et al.: ProlificDreamer: high-fidelity and diverse text-to-3D generation with variational score distillation. In: NeurIPS (2023)"},{"key":"17_CR56","unstructured":"Wei, L.Y., Lefebvre, S., Kwatra, V., Turk, G.: State of the art in example-based texture synthesis. In: EG-STAR (2009)"},{"key":"17_CR57","unstructured":"Xiao, J., Ehinger, K.A., Oliva, A., Torralba, A.: Recognizing scene viewpoint using panoramic place representation. In: ICCV (2012)"},{"key":"17_CR58","doi-asserted-by":"crossref","unstructured":"Zhang, J., Sunkavalli, K., Hold-Geoffroy, Y., Hadap, S., Eisenman, J., Lalonde, J.F.: All-weather deep outdoor lighting estimation. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.01040"}],"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\/978-3-031-73113-6_17","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,20]],"date-time":"2024-11-20T10:11:21Z","timestamp":1732097481000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73113-6_17"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,21]]},"ISBN":["9783031731129","9783031731136"],"references-count":58,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73113-6_17","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,21]]},"assertion":[{"value":"21 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"}}]}}