{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T15:17:54Z","timestamp":1759331874365,"version":"3.40.3"},"publisher-location":"Cham","reference-count":48,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031729881"},{"type":"electronic","value":"9783031729898"}],"license":[{"start":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T00:00:00Z","timestamp":1729900800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T00:00:00Z","timestamp":1729900800000},"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\/978-3-031-72989-8_25","type":"book-chapter","created":{"date-parts":[[2024,10,25]],"date-time":"2024-10-25T17:02:04Z","timestamp":1729875724000},"page":"436-453","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Free-Editor: Zero-Shot Text-Driven 3D Scene Editing"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5522-4456","authenticated-orcid":false,"given":"Nazmul","family":"Karim","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-2162-3367","authenticated-orcid":false,"given":"Hasan","family":"Iqbal","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3357-9720","authenticated-orcid":false,"given":"Umar","family":"Khalid","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3957-7061","authenticated-orcid":false,"given":"Chen","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3981-2933","authenticated-orcid":false,"given":"Jing","family":"Hua","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,10,26]]},"reference":[{"key":"25_CR1","doi-asserted-by":"crossref","unstructured":"Barron, J.T., Mildenhall, B., Tancik, M., Hedman, P., Martin-Brualla, R., Srinivasan, P.P.: Mip-nerf: a multiscale representation for anti-aliasing neural radiance fields. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5855\u20135864 (2021)","DOI":"10.1109\/ICCV48922.2021.00580"},{"key":"25_CR2","doi-asserted-by":"crossref","unstructured":"Barron, J.T., Mildenhall, B., Verbin, D., Srinivasan, P.P., Hedman, P.: Mip-nerf 360: unbounded anti-aliased neural radiance fields. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5470\u20135479 (2022)","DOI":"10.1109\/CVPR52688.2022.00539"},{"key":"25_CR3","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":"25_CR4","doi-asserted-by":"crossref","unstructured":"Chen, A., et al.: Mvsnerf: fast generalizable radiance field reconstruction from multi-view stereo. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 14124\u201314133 (2021)","DOI":"10.1109\/ICCV48922.2021.01386"},{"key":"25_CR5","doi-asserted-by":"crossref","unstructured":"Downs, L., et al.: Google scanned objects: a high-quality dataset of 3D scanned household items. In: 2022 International Conference on Robotics and Automation (ICRA), pp. 2553\u20132560. IEEE (2022)","DOI":"10.1109\/ICRA46639.2022.9811809"},{"key":"25_CR6","unstructured":"Fang, S., et al.: PVD-AL: progressive volume distillation with active learning for efficient conversion between different nerf architectures. arXiv preprint arXiv:2304.04012 (2023)"},{"key":"25_CR7","doi-asserted-by":"crossref","unstructured":"Fang, S., Xu, W., Wang, H., Yang, Y., Wang, Y., Zhou, S.: One is all: bridging the gap between neural radiance fields architectures with progressive volume distillation. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a037, pp. 597\u2013605 (2023)","DOI":"10.1609\/aaai.v37i1.25135"},{"key":"25_CR8","doi-asserted-by":"crossref","unstructured":"Flynn, J., et al.: Deepview: view synthesis with learned gradient descent. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2367\u20132376 (2019)","DOI":"10.1109\/CVPR.2019.00247"},{"key":"25_CR9","doi-asserted-by":"crossref","unstructured":"Gordon, O., Avrahami, O., Lischinski, D.: Blended-nerf: zero-shot object generation and blending in existing neural radiance fields. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2941\u20132951 (2023)","DOI":"10.1109\/ICCVW60793.2023.00316"},{"key":"25_CR10","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":"25_CR11","doi-asserted-by":"crossref","unstructured":"Han, L., Li, Y., Zhang, H., Milanfar, P., Metaxas, D., Yang, F.: Svdiff: compact parameter space for diffusion fine-tuning. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7323\u20137334 (2023)","DOI":"10.1109\/ICCV51070.2023.00673"},{"key":"25_CR12","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":"25_CR13","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"25_CR14","doi-asserted-by":"crossref","unstructured":"H\u00f6llein, L., Johnson, J., Nie\u00dfner, M.: Stylemesh: style transfer for indoor 3D scene reconstructions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6198\u20136208 (2022)","DOI":"10.1109\/CVPR52688.2022.00610"},{"key":"25_CR15","unstructured":"Husz\u00e1r, F.: How (not) to train your generative model: scheduled sampling, likelihood, adversary? arXiv preprint arXiv:1511.05101 (2015)"},{"key":"25_CR16","doi-asserted-by":"crossref","unstructured":"Johari, M.M., Lepoittevin, Y., Fleuret, F.: Geonerf: generalizing nerf with geometry priors. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18365\u201318375 (2022)","DOI":"10.1109\/CVPR52688.2022.01782"},{"key":"25_CR17","unstructured":"Karim, N., Khalid, U., Joneidi, M., Chen, C., Rahnavard, N.: Save: spectral-shift-aware adaptation of image diffusion models for text-driven video editing. arXiv preprint arXiv:2305.18670 (2023)"},{"key":"25_CR18","doi-asserted-by":"crossref","unstructured":"Khalid, U., Iqbal, H., Karim, N., Hua, J., Chen, C.: Latenteditor: text driven local editing of 3D scenes. arXiv preprint arXiv:2312.09313 (2023)","DOI":"10.1007\/978-3-031-73039-9_21"},{"key":"25_CR19","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":"25_CR20","doi-asserted-by":"crossref","unstructured":"Kim, M., Seo, S., Han, B.: Infonerf: ray entropy minimization for few-shot neural volume rendering. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12912\u201312921 (2022)","DOI":"10.1109\/CVPR52688.2022.01257"},{"key":"25_CR21","unstructured":"Kobayashi, S., Matsumoto, E., Sitzmann, V.: Decomposing nerf for editing via feature field distillation. arXiv preprint arXiv:2205.15585 (2022)"},{"key":"25_CR22","unstructured":"Li, J., Li, D., Savarese, S., Hoi, S.: Blip-2: bootstrapping language-image pre-training with frozen image encoders and large language models. In: International Conference on Machine Learning, pp. 19730\u201319742. PMLR (2023)"},{"key":"25_CR23","unstructured":"Liu, L., Gu, J., Zaw Lin, K., et al.: Neural sparse voxel fields. In: NeurIPS 2020, vol. 33, pp. 15651\u201315663 (2020)"},{"key":"25_CR24","doi-asserted-by":"crossref","unstructured":"Liu, Y., et al.: Neural rays for occlusion-aware image-based rendering. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7824\u20137833 (2022)","DOI":"10.1109\/CVPR52688.2022.00767"},{"issue":"4","key":"25_CR25","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":"25_CR26","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":"25_CR27","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":"25_CR28","doi-asserted-by":"crossref","unstructured":"Oechsle, M., Peng, S., Geiger, A.: Unisurf: unifying neural implicit surfaces and radiance fields for multi-view reconstruction. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5589\u20135599 (2021)","DOI":"10.1109\/ICCV48922.2021.00554"},{"key":"25_CR29","doi-asserted-by":"crossref","unstructured":"Park, K., et al.: Nerfies: deformable neural radiance fields. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5865\u20135874 (2021)","DOI":"10.1109\/ICCV48922.2021.00581"},{"key":"25_CR30","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":"25_CR31","doi-asserted-by":"crossref","unstructured":"Ruiz, N., Li, Y., Jampani, V., Pritch, Y., Rubinstein, M., Aberman, K.: Dreambooth: fine tuning text-to-image diffusion models for subject-driven generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 22500\u201322510 (2023)","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"25_CR32","doi-asserted-by":"crossref","unstructured":"Sajjadi, M.S., et al.: Scene representation transformer: geometry-free novel view synthesis through set-latent scene representations. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6229\u20136238 (2022)","DOI":"10.1109\/CVPR52688.2022.00613"},{"key":"25_CR33","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":"25_CR34","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"156","DOI":"10.1007\/978-3-031-19824-3_10","volume-title":"ECCV 2022","author":"M Suhail","year":"2022","unstructured":"Suhail, M., Esteves, C., Sigal, L., Makadia, A.: Generalizable patch-based neural rendering. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13692, pp. 156\u2013174. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19824-3_10"},{"key":"25_CR35","doi-asserted-by":"crossref","unstructured":"Tancik, M., et al.: Block-nerf: scalable large scene neural view synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8248\u20138258 (2022)","DOI":"10.1109\/CVPR52688.2022.00807"},{"key":"25_CR36","doi-asserted-by":"crossref","unstructured":"Tancik, M., et al.: 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":"25_CR37","unstructured":"Tang, J., Chen, X., Wang, J., Zeng, G.: Compressible-composable nerf via rank-residual decomposition. In: Advances in Neural Information Processing Systems, vol. 35, pp. 14798\u201314809 (2022)"},{"key":"25_CR38","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":"25_CR39","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":"25_CR40","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":"25_CR41","unstructured":"Wang, P., Chen, X., Chen, T., Venugopalan, S., Wang, Z., et\u00a0al.: Is attention all nerf needs? arXiv preprint arXiv:2207.13298 (2022)"},{"key":"25_CR42","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":"25_CR43","doi-asserted-by":"crossref","unstructured":"Wang, Q., et al.: Ibrnet: learning multi-view image-based rendering. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4690\u20134699 (2021)","DOI":"10.1109\/CVPR46437.2021.00466"},{"key":"25_CR44","doi-asserted-by":"crossref","unstructured":"Wizadwongsa, S., Phongthawee, P., Yenphraphai, J., Suwajanakorn, S.: Nex: real-time view synthesis with neural basis expansion. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8534\u20138543 (2021)","DOI":"10.1109\/CVPR46437.2021.00843"},{"key":"25_CR45","doi-asserted-by":"crossref","unstructured":"Yang, Z., Ren, Z., Shan, Q., Huang, Q.: MVS2D: efficient multi-view stereo via attention-driven 2D convolutions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8574\u20138584 (2022)","DOI":"10.1109\/CVPR52688.2022.00838"},{"key":"25_CR46","doi-asserted-by":"crossref","unstructured":"Yu, A., Ye, V., Tancik, M., Kanazawa, A.: pixelNeRF: neural radiance fields from one or few images. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4578\u20134587 (2021)","DOI":"10.1109\/CVPR46437.2021.00455"},{"key":"25_CR47","doi-asserted-by":"crossref","unstructured":"Zhou, T., Tucker, R., Flynn, J., Fyffe, G., Snavely, N.: Stereo magnification: learning view synthesis using multiplane images. arXiv preprint arXiv:1805.09817 (2018)","DOI":"10.1145\/3197517.3201323"},{"key":"25_CR48","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\/978-3-031-72989-8_25","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,30]],"date-time":"2024-11-30T08:30:51Z","timestamp":1732955451000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72989-8_25"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,26]]},"ISBN":["9783031729881","9783031729898"],"references-count":48,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72989-8_25","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,10,26]]},"assertion":[{"value":"26 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"}}]}}