{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T03:10:09Z","timestamp":1767323409103,"version":"3.48.0"},"publisher-location":"Singapore","reference-count":29,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819557363","type":"print"},{"value":"9789819557370","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[[2026]]},"DOI":"10.1007\/978-981-95-5737-0_12","type":"book-chapter","created":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T03:07:06Z","timestamp":1767323226000},"page":"163-176","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["ScenePainter: Hierarchical Object-Scene-Object Diffusion-Based Framework for\u00a0Style-Consistent Indoor Scene Texturing"],"prefix":"10.1007","author":[{"given":"Biru","family":"Yang","sequence":"first","affiliation":[]},{"given":"Simo","family":"Zhu","sequence":"additional","affiliation":[]},{"given":"Bin","family":"Wang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2026,1,2]]},"reference":[{"key":"12_CR1","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: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 4169\u20134181 (2023)","DOI":"10.1109\/ICCV51070.2023.00385"},{"key":"12_CR2","doi-asserted-by":"crossref","unstructured":"Chen, D.Z., Li, H., Lee, H.Y., Tulyakov, S., Nie\u00dfner, M.: SceneTex: high-quality texture synthesis for indoor scenes via diffusion priors. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 21081\u201321091 (2024)","DOI":"10.1109\/CVPR52733.2024.01992"},{"key":"12_CR3","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. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2023)","DOI":"10.1109\/ICCV51070.2023.01701"},{"key":"12_CR4","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: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 22246\u201322256 (2023)","DOI":"10.1109\/ICCV51070.2023.02033"},{"key":"12_CR5","doi-asserted-by":"crossref","unstructured":"Fu, H., et al.: 3D-FRONT: 3D furnished rooms with layouts and semaNTics. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2020)","DOI":"10.1109\/ICCV48922.2021.01075"},{"issue":"12","key":"12_CR6","doi-asserted-by":"publisher","first-page":"3313","DOI":"10.1007\/s11263-021-01534-z","volume":"129","author":"H Fu","year":"2020","unstructured":"Fu, H., et al.: 3D-FUTURE: 3D furniture shape with textURE. Int. J. Comput. Vis. 129(12), 3313\u20133337 (2020)","journal-title":"Int. J. Comput. Vis."},{"key":"12_CR7","doi-asserted-by":"crossref","unstructured":"Hertz, A., Voynov, A., Fruchter, S., Cohen-Or, D.: Style aligned image generation via shared attention. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2024)","DOI":"10.1109\/CVPR52733.2024.00457"},{"key":"12_CR8","doi-asserted-by":"crossref","unstructured":"Hessel, J., Holtzman, A., Forbes, M., Bras, R.L., Choi, Y.: CLIPscore: a reference-free evaluation metric for image captioning. In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing (EMNLP) (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"12_CR9","first-page":"6840","volume":"33","author":"J Ho","year":"2020","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. Adv. Neural Inf. Proc. Syst. (NeurIPS) 33, 6840\u20136851 (2020)","journal-title":"Adv. Neural Inf. Proc. Syst. (NeurIPS)"},{"key":"12_CR10","unstructured":"Huang, Z., et al.: Mv-Adapter: multi-view consistent image generation made easy. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2024)"},{"key":"12_CR11","unstructured":"Huang, Z., et al.: RoomPainter: view-integrated diffusion for consistent indoor scene texturing (2024). https:\/\/arxiv.org\/abs\/2412.16778"},{"key":"12_CR12","doi-asserted-by":"crossref","unstructured":"Hwang, I., Kim, H., Kim, Y.M.: Text2Scene: text-driven indoor scene stylization with part-aware details. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2023)","DOI":"10.1109\/CVPR52729.2023.00188"},{"key":"12_CR13","unstructured":"Liu, T., et al.: Free4D: Tuning-free 4D scene generation with spatial-temporal consistency (2025). https:\/\/arxiv.org\/abs\/2503.20785"},{"key":"12_CR14","doi-asserted-by":"crossref","unstructured":"Liu, Y., Xie, M., Liu, H., Wong, T.T.: Text-guided texturing by synchronized multi-view diffusion. In: ACM SIGGRAPH Asia 2024 Conference Proceedings (2024)","DOI":"10.1145\/3680528.3687621"},{"key":"12_CR15","unstructured":"Podell, D., et al.: SDXL: improving latent diffusion models for high-resolution image synthesis. In: International Conference on Learning Representations (ICLR) (2024)"},{"key":"12_CR16","unstructured":"Poole, B., Jain, A., Barron, J.T., Mildenhall, B.: DreamFusion: text-to-3D using 2D diffusion. In: International Conference on Learning Representations (ICLR) (2023)"},{"key":"12_CR17","doi-asserted-by":"crossref","unstructured":"Qiu, L., et al.: RichDreamer: a generalizable normal-depth diffusion model for detail richness in text-to-3D. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 9914\u20139925 (2024)","DOI":"10.1109\/CVPR52733.2024.00946"},{"key":"12_CR18","doi-asserted-by":"crossref","unstructured":"Richardson, E., Metzer, G., Alaluf, Y., Giryes, R., Cohen-Or, D.: TEXTure: text-guided texturing of 3D shapes. In: ACM SIGGRAPH 2023 Conference Papers (2023)","DOI":"10.1145\/3588432.3591503"},{"key":"12_CR19","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"12_CR20","first-page":"36479","volume":"35","author":"C Saharia","year":"2022","unstructured":"Saharia, C., et al.: Photorealistic text-to-image diffusion models with deep language understanding. Adv. Neural Inf. Proc. Syst. (NeurIPS) 35, 36479\u201336494 (2022)","journal-title":"Adv. Neural Inf. Proc. Syst. (NeurIPS)"},{"key":"12_CR21","unstructured":"Schuhmann, C., et al.: LAION-400M: open dataset of clip-filtered 400 million image-text pairs (2021). https:\/\/arxiv.org\/abs\/2111.02114"},{"key":"12_CR22","unstructured":"Shi, Y., Wang, P., Ye, J., Long, M., Li, K., Yang, X.: MVDream: multi-view diffusion for 3D generation. In: International Conference on Learning Representations (ICLR) (2024)"},{"key":"12_CR23","unstructured":"Team, T.H.: Hunyuan3D 2.0: scaling diffusion models for high resolution textured 3D assets generation (2025). https:\/\/arxiv.org\/abs\/2501.12202"},{"key":"12_CR24","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 12619\u201312629 (2023)","DOI":"10.1109\/CVPR52729.2023.01214"},{"key":"12_CR25","doi-asserted-by":"crossref","unstructured":"Wang, Q., et al.: RoomTex: texturing compositional indoor scenes via iterative inpainting. In: European Conference on Computer Vision (ECCV) (2024)","DOI":"10.1007\/978-3-031-73113-6_27"},{"key":"12_CR26","unstructured":"xinsir\/controlnet-depth-sdxl-1.0, April 2023. Hugging Face model repository. https:\/\/huggingface.co\/xinsir\/controlnet-depth-sdxl-1.0"},{"key":"12_CR27","doi-asserted-by":"crossref","unstructured":"Zhang, H., Pan, Z., Zhang, C., Zhu, L., Gao, X.: TexPainter: generative mesh texturing with multi-view consistency. In: ACM SIGGRAPH 2024 Conference Papers (2024). https:\/\/api.semanticscholar.org\/CorpusID:270764653","DOI":"10.1145\/3641519.3657494"},{"key":"12_CR28","doi-asserted-by":"crossref","unstructured":"Zhang, L., Rao, A., Agrawala, M.: Adding conditional control to text-to-image diffusion models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 3836\u20133847 (2023)","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"12_CR29","doi-asserted-by":"crossref","unstructured":"Zhang, Q., et al.: SceneWiz3D: towards text-guided 3D scene composition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2024)","DOI":"10.1109\/CVPR52733.2024.00652"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-5737-0_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T03:07:09Z","timestamp":1767323229000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-5737-0_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819557363","9789819557370"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-5737-0_12","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"2 January 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision  (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Shanghai","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 October 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 October 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/2025.prcv.cn\/index.asp","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}