{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,12]],"date-time":"2026-02-12T17:39:50Z","timestamp":1770917990651,"version":"3.50.1"},"publisher-location":"Cham","reference-count":55,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031730382","type":"print"},{"value":"9783031730399","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T00:00:00Z","timestamp":1730332800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T00:00:00Z","timestamp":1730332800000},"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\/978-3-031-73039-9_21","type":"book-chapter","created":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T14:57:07Z","timestamp":1730300227000},"page":"364-380","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["LatentEditor: Text Driven Local Editing of\u00a03D Scenes"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3357-9720","authenticated-orcid":false,"given":"Umar","family":"Khalid","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0005-2162-3367","authenticated-orcid":false,"given":"Hasan","family":"Iqbal","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5522-4456","authenticated-orcid":false,"given":"Nazmul","family":"Karim","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2658-2494","authenticated-orcid":false,"given":"Muhammad","family":"Tayyab","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3981-2933","authenticated-orcid":false,"given":"Jing","family":"Hua","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3957-7061","authenticated-orcid":false,"given":"Chen","family":"Chen","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,10,31]]},"reference":[{"key":"21_CR1","doi-asserted-by":"crossref","unstructured":"Avrahami, O., Lischinski, D., Fried, O.: Blended diffusion for text-driven editing of natural images. In: CVPR 2022, pp. 18208\u201318218 (2022)","DOI":"10.1109\/CVPR52688.2022.01767"},{"key":"21_CR2","doi-asserted-by":"crossref","unstructured":"Brooks, T., Holynski, A., Efros, A.A.: InstructPix2Pix: learning to follow image editing instructions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18392\u201318402 (2023)","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"21_CR3","unstructured":"Chen, J., et al.: Animatable neural radiance fields from monocular RGB videos. arXiv preprint arXiv:2106.13629 (2021)"},{"key":"21_CR4","unstructured":"Couairon, G., Verbeek, J., Schwenk, H., Cord, M.: DiffEdit: diffusion-based semantic image editing with mask guidance. In: The Eleventh International Conference on Learning Representations (2023). https:\/\/openreview.net\/forum?id=3lge0p5o-M-"},{"key":"21_CR5","doi-asserted-by":"publisher","unstructured":"Frakes, E., Khalid, U., Chen, C.: Efficient and consistent zero-shot video generation with diffusion models. In: Kehtarnavaz, N., Shirvaikar, M.V. (eds.) Real-Time Image Processing and Deep Learning 2024, vol. 13034, p. 1303407. International Society for Optics and Photonics, SPIE (2024). https:\/\/doi.org\/10.1117\/12.3013575","DOI":"10.1117\/12.3013575"},{"key":"21_CR6","doi-asserted-by":"crossref","unstructured":"Gordon, O., Avrahami, O., Lischinski, D.: Blended-NeRF: zero-shot object generation and blending in existing neural radiance fields. arXiv preprint arXiv:2306.12760 (2023)","DOI":"10.1109\/ICCVW60793.2023.00316"},{"key":"21_CR7","unstructured":"Gu, J., Liu, L., Wang, P., Theobalt, C.: StyleNeRF: a style-based 3D-aware generator for high-resolution image synthesis. arXiv preprint arXiv:2110.08985 (2021)"},{"key":"21_CR8","doi-asserted-by":"crossref","unstructured":"Haque, A., Tancik, M., Efros, A.A., Holynski, A., Kanazawa, A.: Instruct-NeRF2NeRF: editing 3D scenes with instructions. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 19740\u201319750 (2023)","DOI":"10.1109\/ICCV51070.2023.01808"},{"key":"21_CR9","unstructured":"Hertz, A., Mokady, R., Tenenbaum, J., Aberman, K., Pritch, Y., Cohen-Or, D.: Prompt-to-prompt image editing with cross attention control. arXiv preprint arXiv:2208.01626 (2022)"},{"key":"21_CR10","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. In: Advances in Neural Information Processing Systems, vol. 33, pp. 6840\u20136851 (2020)"},{"key":"21_CR11","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"372","DOI":"10.1007\/978-3-031-45673-2_37","volume-title":"MLMI 2023","author":"H Iqbal","year":"2023","unstructured":"Iqbal, H., Khalid, U., Chen, C., Hua, J.: Unsupervised anomaly detection in medical images using masked diffusion model. In: Cao, X., Xu, X., Rekik, I., Cui, Z., Ouyang, X. (eds.) MLMI 2023. LNCS, vol. 14348, pp. 372\u2013381. Springer, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-45673-2_37"},{"key":"21_CR12","doi-asserted-by":"crossref","unstructured":"Jain, A., Mildenhall, B., Barron, J.T., Abbeel, P., Poole, B.: Zero-shot text-guided object generation with dream fields. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 867\u2013876 (2022)","DOI":"10.1109\/CVPR52688.2022.00094"},{"key":"21_CR13","doi-asserted-by":"crossref","unstructured":"Karim, N., Khalid, U., Iqbal, H., Hua, J., Chen, C.: Free-editor: zero-shot text-driven 3D scene editing. arXiv preprint arXiv:2312.13663 (2023)","DOI":"10.1007\/978-3-031-72989-8_25"},{"key":"21_CR14","doi-asserted-by":"crossref","unstructured":"Kawar, B., et al.: Imagic: text-based real image editing with diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6007\u20136017 (2023)","DOI":"10.1109\/CVPR52729.2023.00582"},{"key":"21_CR15","doi-asserted-by":"crossref","unstructured":"Kim, H., Lee, G., Choi, Y., Kim, J.H., Zhu, J.Y.: 3D-aware blending with generative nerfs. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 22906\u201322918 (2023)","DOI":"10.1109\/ICCV51070.2023.02094"},{"key":"21_CR16","unstructured":"Krishnamoorthy, A., Menon, D.: Matrix inversion using Cholesky decomposition. In: 2013 Signal Processing: Algorithms, Architectures, Arrangements, and Applications (SPA), pp. 70\u201372. IEEE (2013)"},{"key":"21_CR17","doi-asserted-by":"crossref","unstructured":"Kuang, Z., Luan, F., Bi, S., Shu, Z., Wetzstein, G., Sunkavalli, K.: PaletteNeRF: palette-based appearance editing of neural radiance fields. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 20691\u201320700 (2023)","DOI":"10.1109\/CVPR52729.2023.01982"},{"key":"21_CR18","doi-asserted-by":"crossref","unstructured":"Li, L.H., et\u00a0al.: Grounded language-image pre-training. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10965\u201310975 (2022)","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"21_CR19","unstructured":"Liu, H.K., Shen, I., Chen, B.Y., et\u00a0al.: NeRF-in: free-form nerf inpainting with RGB-D priors. arXiv preprint arXiv:2206.04901 (2022)"},{"key":"21_CR20","unstructured":"Liu, L., Gu, J., Zaw Lin, K., et al.: Neural sparse voxel fields. In: NeurIPS, vol. 2020, no. 33, pp. 15651\u201315663 (2020)"},{"key":"21_CR21","doi-asserted-by":"crossref","unstructured":"Liu, R., Wu, R., Van\u00a0Hoorick, B., Tokmakov, P., Zakharov, S., Vondrick, C.: Zero-1-to-3: zero-shot one image to 3D object. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9298\u20139309 (2023)","DOI":"10.1109\/ICCV51070.2023.00853"},{"key":"21_CR22","doi-asserted-by":"crossref","unstructured":"Liu, S., Zhang, X., Zhang, Z., Zhang, R., Zhu, J.Y., Russell, B.: Editing conditional radiance fields. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5773\u20135783 (2021)","DOI":"10.1109\/ICCV48922.2021.00572"},{"key":"21_CR23","unstructured":"Meng, C., et al.: SDEdit: guided image synthesis and editing with stochastic differential equations. In: International Conference on Learning Representations (2021)"},{"key":"21_CR24","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12663\u201312673 (2023)","DOI":"10.1109\/CVPR52729.2023.01218"},{"key":"21_CR25","doi-asserted-by":"crossref","unstructured":"Mikaeili, A., Perel, O., Safaee, M., Cohen-Or, D., Mahdavi-Amiri, A.: SKED: sketch-guided text-based 3D editing. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 14607\u201314619 (2023)","DOI":"10.1109\/ICCV51070.2023.01343"},{"issue":"4","key":"21_CR26","doi-asserted-by":"publisher","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(4), 1\u201314 (2019)","journal-title":"ACM Trans. Graph. (TOG)"},{"issue":"1","key":"21_CR27","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1145\/3503250","volume":"65","author":"B Mildenhall","year":"2021","unstructured":"Mildenhall, B., Srinivasan, P.P., Tancik, M., Barron, J.T., Ramamoorthi, R., Ng, R.: NeRF: representing scenes as neural radiance fields for view synthesis. Commun. ACM 65(1), 99\u2013106 (2021)","journal-title":"Commun. ACM"},{"issue":"4","key":"21_CR28","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3528223.3530127","volume":"41","author":"T M\u00fcller","year":"2022","unstructured":"M\u00fcller, T., Evans, A., Schied, C., Keller, A.: Instant neural graphics primitives with a multiresolution hash encoding. ACM Trans. Graph. (ToG) 41(4), 1\u201315 (2022)","journal-title":"ACM Trans. Graph. (ToG)"},{"key":"21_CR29","unstructured":"Nichol, A., et al: GLIDE: towards photorealistic image generation and editing with text-guided diffusion models. arXiv preprint arXiv:2112.10741 (2021)"},{"issue":"2","key":"21_CR30","doi-asserted-by":"publisher","first-page":"3336","DOI":"10.1016\/j.eswa.2008.01.039","volume":"36","author":"HS Park","year":"2009","unstructured":"Park, H.S., Jun, C.H.: A simple and fast algorithm for K-medoids clustering. Expert Syst. Appl. 36(2), 3336\u20133341 (2009)","journal-title":"Expert Syst. Appl."},{"issue":"6","key":"21_CR31","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3618321","volume":"42","author":"K Park","year":"2023","unstructured":"Park, K., Henzler, P., Mildenhall, B., Barron, J.T., Martin-Brualla, R.: CamP: camera preconditioning for neural radiance fields. ACM Trans. Graph. (TOG) 42(6), 1\u201311 (2023)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"21_CR32","doi-asserted-by":"crossref","unstructured":"Ponimatkin, G., Labb\u00e9, Y., Russell, B., Aubry, M., Sivic, J.: Focal length and object pose estimation via render and compare. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3825\u20133834 (2022)","DOI":"10.1109\/CVPR52688.2022.00380"},{"key":"21_CR33","unstructured":"Poole, B., Jain, A., Barron, J.T., Mildenhall, B.: DreamFusion: text-to-3D using 2D diffusion. In: The Eleventh International Conference on Learning Representations (2023). https:\/\/openreview.net\/forum?id=FjNys5c7VyY"},{"key":"21_CR34","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"21_CR35","doi-asserted-by":"crossref","unstructured":"Raj, A., et\u00a0al.: DreamBooth3D: subject-driven text-to-3D generation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2349\u20132359 (2023)","DOI":"10.1109\/ICCV51070.2023.00223"},{"key":"21_CR36","unstructured":"Raji\u010d, F., Ke, L., Tai, Y.W., Tang, C.K., Danelljan, M., Yu, F.: Segment anything meets point tracking. arXiv preprint arXiv:2307.01197 (2023)"},{"key":"21_CR37","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":"21_CR38","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, pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"21_CR39","unstructured":"Saharia, C., Chan, W., Saxena, S.E.A.: Photorealistic text-to-image diffusion models with deep language understanding. In: NeurIPS 2022, vol. 35, pp. 36479\u201336494 (2022)"},{"key":"21_CR40","doi-asserted-by":"crossref","unstructured":"Sella, E., Fiebelman, G., Hedman, P., Averbuch-Elor, H.: Vox-E: text-guided voxel editing of 3D objects. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 430\u2013440 (2023)","DOI":"10.1109\/ICCV51070.2023.00046"},{"key":"21_CR41","doi-asserted-by":"crossref","unstructured":"Shao, R., et al.: Control4D: efficient 4D portrait editing with text. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4556\u20134567 (2024)","DOI":"10.1109\/CVPR52733.2024.00436"},{"key":"21_CR42","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. arXiv preprint arXiv:2010.02502 (2020)"},{"key":"21_CR43","doi-asserted-by":"crossref","unstructured":"Suvorov, R., et al.: Resolution-robust large mask inpainting with Fourier convolutions. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 2149\u20132159 (2022)","DOI":"10.1109\/WACV51458.2022.00323"},{"key":"21_CR44","doi-asserted-by":"crossref","unstructured":"Tancik, M., et\u00a0al.: Nerfstudio: a modular framework for neural radiance field development. In: ACM SIGGRAPH 2023 Conference Proceedings, pp. 1\u201312 (2023)","DOI":"10.1145\/3588432.3591516"},{"key":"21_CR45","unstructured":"Touvron, H., et\u00a0al.: Llama 2: open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)"},{"key":"21_CR46","doi-asserted-by":"crossref","unstructured":"Wang, C., Chai, M., He, M., et\u00a0al.: CLIP-NeRF: text-and-image driven manipulation of neural radiance fields. In: CVPR 2022, pp. 3835\u20133844 (2022)","DOI":"10.1109\/CVPR52688.2022.00381"},{"key":"21_CR47","doi-asserted-by":"crossref","unstructured":"Wang, C., Jiang, R., Chai, M., He, M., Chen, D., Liao, J.: NeRF-Art: text-driven neural radiance fields stylization. IEEE Trans. Vis. Comput. Graph. (2023)","DOI":"10.1109\/TVCG.2023.3283400"},{"key":"21_CR48","doi-asserted-by":"crossref","unstructured":"Wang, C., Wu, X., Guo, Y.C., et\u00a0al.: NeRF-SR: high quality neural radiance fields using supersampling. In: ACM MM 2022, pp. 6445\u20136454 (2022)","DOI":"10.1145\/3503161.3547808"},{"key":"21_CR49","unstructured":"Wang, P., Liu, L., Liu, Y., Theobalt, C., Komura, T., Wang, W.: NeuS: learning neural implicit surfaces by volume rendering for multi-view reconstruction. arXiv preprint arXiv:2106.10689 (2021)"},{"key":"21_CR50","doi-asserted-by":"crossref","unstructured":"Xiang, F., Xu, Z., Hasan, M., et\u00a0al.: NeuTex: neural texture mapping for volumetric neural rendering. In: CVPR 2021, pp. 7119\u20137128 (2021)","DOI":"10.1109\/CVPR46437.2021.00704"},{"key":"21_CR51","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"597","DOI":"10.1007\/978-3-031-19787-1_34","volume-title":"ECCV 2022","author":"B Yang","year":"2022","unstructured":"Yang, B., Bao, C., Zeng, J.E.A.: NeuMesh: learning disentangled neural mesh-based implicit field for geometry and texture editing. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13676, pp. 597\u2013614. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19787-1_34"},{"key":"21_CR52","doi-asserted-by":"crossref","unstructured":"Ye, M., Danelljan, M., Yu, F., Ke, L.: Gaussian grouping: segment and edit anything in 3D scenes. arXiv preprint arXiv:2312.00732 (2023)","DOI":"10.1007\/978-3-031-73397-0_10"},{"key":"21_CR53","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"717","DOI":"10.1007\/978-3-031-19821-2_41","volume-title":"ECCV 2022","author":"K Zhang","year":"2022","unstructured":"Zhang, K., et al.: ARF: artistic radiance fields. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13691, pp. 717\u2013733. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19821-2_41"},{"key":"21_CR54","unstructured":"Zhang, K., Riegler, G., Snavely, N., Koltun, V.: NeRF++: analyzing and improving neural radiance fields. arXiv preprint arXiv:2010.07492 (2020)"},{"key":"21_CR55","doi-asserted-by":"crossref","unstructured":"Zhuang, J., Wang, C., Lin, L., Liu, L., Li, G.: DreamEditor: text-driven 3D scene editing with neural fields. In: SIGGRAPH Asia 2023 Conference Papers, pp. 1\u201310 (2023)","DOI":"10.1145\/3610548.3618190"}],"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\/978-3-031-73039-9_21","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,30]],"date-time":"2024-11-30T14:15:42Z","timestamp":1732976142000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73039-9_21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,31]]},"ISBN":["9783031730382","9783031730399"],"references-count":55,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73039-9_21","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,31]]},"assertion":[{"value":"31 October 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"}}]}}