{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,13]],"date-time":"2026-09-13T17:03:48Z","timestamp":1789319028768,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":108,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032368386","type":"print"},{"value":"9783032368393","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\/978-3-032-36839-3_27","type":"book-chapter","created":{"date-parts":[[2026,9,13]],"date-time":"2026-09-13T16:26:14Z","timestamp":1789316774000},"page":"494-514","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["EditVerse3D: High-Quality 3D Object Editing with\u00a0Region-Aware Learning"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7321-7927","authenticated-orcid":false,"given":"Youtan","family":"Yin","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanning","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiacheng","family":"Wei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaofeng","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiayang","family":"Bai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingwen","family":"Ye","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weidong","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guosheng","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,14]]},"reference":[{"key":"27_CR1","unstructured":"Bar-On, R., Cohen-Bar, D., Cohen-Or, D.: EditP23: 3D editing via propagation of image prompts to multi-view (2025). https:\/\/arxiv.org\/abs\/2506.20652"},{"key":"27_CR2","doi-asserted-by":"crossref","unstructured":"Barda, A., Gadelha, M., Kim, V.G., Aigerman, N., Bermano, A.H., Groueix, T.: Instant3Dit: multiview inpainting for fast editing of 3D objects. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16273\u201316282 (2025)","DOI":"10.1109\/CVPR52734.2025.01517"},{"key":"27_CR3","doi-asserted-by":"publisher","unstructured":"Bokhovkin, A., Meng, Q., Tulsiani, S., Dai, A.: SceneFactor: factored latent 3D diffusion for controllable 3D scene generation (2024). https:\/\/doi.org\/10.48550\/arXiv.2412.01801","DOI":"10.48550\/arXiv.2412.01801"},{"key":"27_CR4","doi-asserted-by":"publisher","unstructured":"Cen, J., et al.: Segment any 3D gaussians (2025). https:\/\/doi.org\/10.48550\/arXiv.2312.00860","DOI":"10.48550\/arXiv.2312.00860"},{"key":"27_CR5","unstructured":"Chen, H., et al.: Generic 3D diffusion adapter using controlled multi-view editing (2024). https:\/\/arxiv.org\/abs\/2403.12032"},{"key":"27_CR6","doi-asserted-by":"crossref","unstructured":"Chen, M., et al.: PartGen: part-level 3D generation and reconstruction with multi-view diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5881\u20135892 (2025)","DOI":"10.1109\/CVPR52734.2025.00552"},{"key":"27_CR7","doi-asserted-by":"crossref","unstructured":"Chen, M., Xie, J., Laina, I., Vedaldi, A.: Shap-editor: instruction-guided latent 3D editing in seconds. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 26456\u201326466 (2024)","DOI":"10.1109\/CVPR52733.2024.02498"},{"key":"27_CR8","doi-asserted-by":"publisher","unstructured":"Chen, T., et al.: Reasoning3D \u2013 grounding and reasoning in 3D: Fine-grained zero-shot open-vocabulary 3D reasoning part segmentation via large vision-language models (2024). https:\/\/doi.org\/10.48550\/arXiv.2405.19326","DOI":"10.48550\/arXiv.2405.19326"},{"key":"27_CR9","doi-asserted-by":"publisher","unstructured":"Chen, Y., Hu, T., Tang, Y., Chen, S., Chen, A., Yi, R.: Plasticine3D: 3D non-rigid editing with text guidance by multi-view embedding optimization (2024). https:\/\/doi.org\/10.48550\/arXiv.2312.10111","DOI":"10.48550\/arXiv.2312.10111"},{"key":"27_CR10","doi-asserted-by":"publisher","unstructured":"Chen, Y., et al.: Ultra3D: efficient and high-fidelity 3D generation with part attention (2025). https:\/\/doi.org\/10.48550\/arXiv.2507.17745","DOI":"10.48550\/arXiv.2507.17745"},{"key":"27_CR11","doi-asserted-by":"publisher","unstructured":"Choi, C., Lee, J., Park, J., Kim, Y.M.: 3DOODLE: compact abstraction of objects with 3D strokes. ACM Trans. Graph. (TOG) (2024). https:\/\/doi.org\/10.1145\/3658156","DOI":"10.1145\/3658156"},{"key":"27_CR12","unstructured":"Darcet, T., Oquab, M., Mairal, J., Bojanowski, P.: Vision transformers need registers (2023)"},{"key":"27_CR13","doi-asserted-by":"crossref","unstructured":"Deitke, M., et al.: Objaverse-XL: a universe of 10M+ 3D objects. arXiv preprint arXiv:2307.05663 (2023)","DOI":"10.52202\/075280-1554"},{"key":"27_CR14","doi-asserted-by":"crossref","unstructured":"Deitke, M., et al.: Objaverse: a universe of annotated 3D objects. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13142\u201313153 (2023)","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"27_CR15","unstructured":"Deng, Y., He, X., Mei, C., Wang, P., Tang, F.: FireFow: fast inversion of rectified flow for image semantic editing. In: Forty-Second International Conference on Machine Learning (2025)"},{"key":"27_CR16","doi-asserted-by":"crossref","unstructured":"Dinh, N.A., Lang, I., Kim, H., Stein, O., Hanocka, R.: Geometry in style: 3D stylization via surface normal deformation (2025).https:\/\/arxiv.org\/abs\/2503.23241","DOI":"10.1109\/CVPR52734.2025.02650"},{"key":"27_CR17","doi-asserted-by":"crossref","unstructured":"Dong, S., Ding, L., Huang, Z., Wang, Z., Xue, T., Xu, D.: Interactive3D: create what you want by interactive 3D generation (2024).https:\/\/arxiv.org\/abs\/2404.16510","DOI":"10.1109\/CVPR52733.2024.00478"},{"key":"27_CR18","doi-asserted-by":"crossref","unstructured":"Erko\u00e7, Z., et ak.: Preditor3D: fast and precise 3D shape editing. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 640\u2013649 (2025)","DOI":"10.1109\/CVPR52734.2025.00068"},{"key":"27_CR19","doi-asserted-by":"crossref","unstructured":"Fan, H., Su, H., Guibas, L.J.: A point set generation network for 3D object reconstruction from a single image. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 605\u2013613 (2017)","DOI":"10.1109\/CVPR.2017.264"},{"key":"27_CR20","doi-asserted-by":"publisher","unstructured":"Fang, S., et al.: Chat-edit-3D: interactive 3D scene editing via\u00a0text prompts. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds.) Computer Vision \u2013 ECCV 2024, pp. 199\u2013216. Springer Nature Switzerland, Cham (2025). https:\/\/doi.org\/10.1007\/978-3-031-72946-1_12","DOI":"10.1007\/978-3-031-72946-1_12"},{"key":"27_CR21","doi-asserted-by":"publisher","unstructured":"Fischer, M., Georgiev, I., Groueix, T., Kim, V.G., Ritschel, T., Deschaintre, V.: Sama: material-aware 3D selection and segmentation (2024). https:\/\/doi.org\/10.48550\/arXiv.2411.19322","DOI":"10.48550\/arXiv.2411.19322"},{"key":"27_CR22","doi-asserted-by":"crossref","unstructured":"Gao, W., et al.: 3D mesh editing using masked LRMS (2025). https:\/\/arxiv.org\/abs\/2412.08641","DOI":"10.1109\/ICCV51701.2025.00672"},{"key":"27_CR23","doi-asserted-by":"publisher","unstructured":"Gao, Z., Yi, R., Huang, Y., Chen, W., Zhu, C., Xu, K.: Self-supervised learning of hybrid part-aware 3d representations of 2D gaussians and superquadrics (2025). https:\/\/doi.org\/10.48550\/arXiv.2408.10789","DOI":"10.48550\/arXiv.2408.10789"},{"key":"27_CR24","unstructured":"Google: Google Gemini (2025). https:\/\/gemini.google.com\/app"},{"key":"27_CR25","doi-asserted-by":"publisher","unstructured":"Han, X., Tian, R., Tong, Y., Yu, F., Liu, D., Zhang, Y.: ARAP-GS: drag-driven as-rigid-as-possible 3D gaussian splatting editing with diffusion prior (2025). https:\/\/doi.org\/10.48550\/arXiv.2504.12788","DOI":"10.48550\/arXiv.2504.12788"},{"key":"27_CR26","doi-asserted-by":"crossref","unstructured":"He, K., Wu, C.H., Gilitschenski, I.: Ctrl-D: controllable dynamic 3D scene editing with personalized 2D diffusion. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 26630\u201326640 (2025)","DOI":"10.1109\/CVPR52734.2025.02480"},{"key":"27_CR27","doi-asserted-by":"publisher","unstructured":"He, X., et al.: SparseFlex: high-resolution and arbitrary-topology 3D shape modeling (2025). https:\/\/doi.org\/10.48550\/arXiv.2503.21732","DOI":"10.48550\/arXiv.2503.21732"},{"key":"27_CR28","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. In: Advances in Neural Information Processing Systems, vol. 30, Curran Associates, Inc. (2017)"},{"key":"27_CR29","doi-asserted-by":"publisher","unstructured":"Hong, Y., et al.: Towards generalized and training-free text-guided semantic manipulation (2025). https:\/\/doi.org\/10.48550\/arXiv.2504.17269","DOI":"10.48550\/arXiv.2504.17269"},{"key":"27_CR30","doi-asserted-by":"publisher","unstructured":"Jincheng, J., Cai, Y., Liu, L.: CraftMesh: high-fidelity generative mesh manipulation via poisson seamless fusion (2025). https:\/\/doi.org\/10.48550\/arXiv.2509.13688","DOI":"10.48550\/arXiv.2509.13688"},{"key":"27_CR31","doi-asserted-by":"crossref","unstructured":"Jose, C., et al.: DINOv2 meets text: a unified framework for image- and pixel-level vision-language alignment (2024)","DOI":"10.1109\/CVPR52734.2025.02319"},{"key":"27_CR32","doi-asserted-by":"publisher","unstructured":"Ju, X., Liu, X., Wang, X., Bian, Y., Shan, Y., Xu, Q.: BrushNet: a plug-and-play image inpainting model with\u00a0decomposed dual-branch diffusion. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds.) Computer Vision \u2013 ECCV 2024, pp. 150\u2013168. Springer Nature Switzerland, Cham (2025). https:\/\/doi.org\/10.1007\/978-3-031-72661-3_9","DOI":"10.1007\/978-3-031-72661-3_9"},{"issue":"4","key":"27_CR33","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3592433","volume":"42","author":"B Kerbl","year":"2023","unstructured":"Kerbl, B., Kopanas, G., Leimkuehler, T., Drettakis, G.: 3D gaussian splatting for real-time radiance field rendering. ACM Trans. Graph. 42(4), 1\u201314 (2023). https:\/\/doi.org\/10.1145\/3592433","journal-title":"ACM Trans. Graph."},{"key":"27_CR34","unstructured":"Kim, J., Lee, S., Shin, J., Choi, J., Shim, H.: DreamCatalyst: fast and high-quality 3D editing via controlling editability and identity preservation. In: The Thirteenth International Conference on Learning Representations (2024)"},{"key":"27_CR35","doi-asserted-by":"publisher","unstructured":"Kulikov, V., Kleiner, M., Huberman-Spiegelglas, I., Michaeli, T.: FLOWEDIT: inversion-free text-based editing using pre-trained flow models (2025). https:\/\/doi.org\/10.48550\/arXiv.2412.08629","DOI":"10.48550\/arXiv.2412.08629"},{"key":"27_CR36","unstructured":"Labs, B.F., et al.: Flux.1 KONTEXT: flow matching for in-context image generation and editing in latent space (2025). https:\/\/arxiv.org\/abs\/2506.15742"},{"key":"27_CR37","doi-asserted-by":"publisher","unstructured":"Lai, Z., et al.: Unleashing VECSET diffusion model for fast shape generation (2025). https:\/\/doi.org\/10.48550\/arXiv.2503.16302","DOI":"10.48550\/arXiv.2503.16302"},{"key":"27_CR38","unstructured":"Lan, Y., et al.: GaussianAnything: interactive point cloud flow matching for 3D generation. In: International Conference on Representation Learning, vol. 2025, pp. 97419\u201397443 (2025)"},{"key":"27_CR39","doi-asserted-by":"publisher","unstructured":"Le, D.H., Pham, T., Kembhavi, A., Mandt, S., Ma, W.C., Lu, J.: Preserving identity with variational score for general-purpose 3D editing (2024). https:\/\/doi.org\/10.48550\/arXiv.2406.08953","DOI":"10.48550\/arXiv.2406.08953"},{"key":"27_CR40","doi-asserted-by":"publisher","unstructured":"Li, H., et al.: Text-to-3D generation by 2D editing (2025). https:\/\/doi.org\/10.48550\/arXiv.2412.05929","DOI":"10.48550\/arXiv.2412.05929"},{"key":"27_CR41","doi-asserted-by":"publisher","unstructured":"Li, H., Erkocet al.: MESHPAD: interactive sketch-conditioned artist-reminiscent mesh generation and editing (2025). https:\/\/doi.org\/10.48550\/arXiv.2503.01425","DOI":"10.48550\/arXiv.2503.01425"},{"key":"27_CR42","doi-asserted-by":"publisher","unstructured":"Li, L., et al.: VOXHAMMER: training-free precise and coherent 3D editing in native 3D space (2025). https:\/\/doi.org\/10.48550\/arXiv.2508.19247","DOI":"10.48550\/arXiv.2508.19247"},{"key":"27_CR43","doi-asserted-by":"publisher","unstructured":"Li, P., et al.: CMD: controllable multiview diffusion for 3D editing and progressive generation. In: Proceedings of the Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers, pp. 1\u201310. ACM, Vancouver BC Canada (2025). https:\/\/doi.org\/10.1145\/3721238.3730722","DOI":"10.1145\/3721238.3730722"},{"key":"27_CR44","doi-asserted-by":"publisher","unstructured":"Li, W., et al.: Step1x-3D: Towards high-fidelity and controllable generation of textured 3D assets (2025). https:\/\/doi.org\/10.48550\/arXiv.2505.07747","DOI":"10.48550\/arXiv.2505.07747"},{"key":"27_CR45","doi-asserted-by":"crossref","unstructured":"Lin, J., et al.: Kiss3DGEN: repurposing image diffusion models for 3D asset generation. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 5870\u20135880 (2025)","DOI":"10.1109\/CVPR52734.2025.00551"},{"key":"27_CR46","doi-asserted-by":"publisher","unstructured":"Lin, Y., et al.: PartCrafter: structured 3D mesh generation via compositional latent diffusion transformers (2025). https:\/\/doi.org\/10.48550\/arXiv.2506.05573","DOI":"10.48550\/arXiv.2506.05573"},{"key":"27_CR47","unstructured":"Lipman, Y., Chen, R.T.Q., Ben-Hamu, H., Nickel, M., Le, M.: Flow matching for generative modeling (2023). https:\/\/arxiv.org\/abs\/2210.02747"},{"key":"27_CR48","doi-asserted-by":"crossref","unstructured":"Liu, F., Wang, H., Chen, W., Sun, H., Duan, Y.: Make-your-3D: fast and consistent subject-driven 3D content generation (2024). https:\/\/arxiv.org\/abs\/2403.09625","DOI":"10.1007\/978-3-031-72907-2_23"},{"issue":"4","key":"27_CR49","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3658120","volume":"43","author":"FL Liu","year":"2024","unstructured":"Liu, F.L., Fu, H., Lai, Y.K., Gao, L.: SketchDream: sketch-based text-to-3D generation and editing. ACM Trans. Graph. 43(4), 1\u201313 (2024). https:\/\/doi.org\/10.1145\/3658120","journal-title":"ACM Trans. Graph."},{"key":"27_CR50","doi-asserted-by":"crossref","unstructured":"Liu, M., et al.: PartField: learning 3D feature fields for part segmentation and beyond (2025)","DOI":"10.1109\/ICCV51701.2025.00905"},{"key":"27_CR51","doi-asserted-by":"crossref","unstructured":"Long, X., et al.: Wonder3D: single image to 3D using cross-domain diffusion. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9970\u20139980 (2024)","DOI":"10.1109\/CVPR52733.2024.00951"},{"key":"27_CR52","doi-asserted-by":"crossref","unstructured":"Lu, R., et al.: MOVIS: enhancing multi-object novel view synthesis for indoor scenes. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 26767\u201326778 (2025)","DOI":"10.1109\/CVPR52734.2025.02493"},{"key":"27_CR53","doi-asserted-by":"publisher","unstructured":"Lu, Y., et al.: Orientation matters: making 3D generative models orientation-aligned (2025). https:\/\/doi.org\/10.48550\/arXiv.2506.08640","DOI":"10.48550\/arXiv.2506.08640"},{"key":"27_CR54","doi-asserted-by":"publisher","unstructured":"Lugmayr, A., Danelljan, M., Romero, A., Yu, F., Timofte, R., Van\u00a0Gool, L.: Repaint: inpainting using denoising diffusion probabilistic models. In: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 11451\u201311461 (2022). https:\/\/doi.org\/10.1109\/CVPR52688.2022.01117","DOI":"10.1109\/CVPR52688.2022.01117"},{"key":"27_CR55","unstructured":"Ma, C., et al.: P3-SAM: native 3D part segmentation. arXiv preprint arXiv:2509.06784 (2025)"},{"key":"27_CR56","doi-asserted-by":"publisher","unstructured":"Ma, Z., Yue, Y., Gkioxari, G.: Find any part in 3D (2025). https:\/\/doi.org\/10.48550\/arXiv.2411.13550","DOI":"10.48550\/arXiv.2411.13550"},{"key":"27_CR57","unstructured":"Meng, C., et al.: SDEDIT: guided image synthesis and editing with stochastic differential equations. In: International Conference on Learning Representations (2021)"},{"key":"27_CR58","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":"1","key":"27_CR59","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1145\/3503250","volume":"65","author":"B Mildenhall","year":"2022","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 (2022). https:\/\/doi.org\/10.1145\/3503250","journal-title":"Commun. ACM"},{"key":"27_CR60","unstructured":"Oquab, M., et al.: Dinov2: learning robust visual features without supervision (2023)"},{"key":"27_CR61","doi-asserted-by":"publisher","unstructured":"Parelli, M., Oechsle, M., Niemeyer, M., Tombari, F., Geiger, A.: 3D-latte: latent space 3D editing from textual instructions (2025). https:\/\/doi.org\/10.48550\/arXiv.2509.00269","DOI":"10.48550\/arXiv.2509.00269"},{"key":"27_CR62","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 (2022)"},{"key":"27_CR63","unstructured":"Qi, Z., et al.: Tailor3D: customized 3D assets editing and generation with dual-side images (2024). https:\/\/arxiv.org\/abs\/2407.06191"},{"key":"27_CR64","doi-asserted-by":"crossref","unstructured":"Ren, Y., Jiang, Z., Zhang, T., Forchhammer, S., S\u00fcsstrunk, S.: FDS: frequency-aware denoising score for text-guided latent diffusion image editing. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 2651\u20132660 (2025)","DOI":"10.1109\/CVPR52734.2025.00253"},{"key":"27_CR65","doi-asserted-by":"publisher","unstructured":"Rojas, S., Philip, J., Zhang, K., Bi, S., Luan, F., Ghanem, B., Sunkavalli, K.: DateNERF: depth-aware text-based editing of\u00a0nerfs. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds.) Computer Vision \u2013 ECCV 2024, pp. 267\u2013284. Springer Nature Switzerland, Cham (2025). https:\/\/doi.org\/10.1007\/978-3-031-73247-8_16","DOI":"10.1007\/978-3-031-73247-8_16"},{"key":"27_CR66","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), pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"27_CR67","unstructured":"Rout, L., Chen, Y., Ruiz, N., Caramanis, C., Shakkottai, S., Chu, W.S.: Semantic image inversion and editing using rectified stochastic differential equations. In: The Thirteenth International Conference on Learning Representations (2024)"},{"key":"27_CR68","doi-asserted-by":"crossref","unstructured":"Sella, E., Atia, N., Mokady, R., Averbuch-Elor, H.: Blended point cloud diffusion for localized text-guided shape editing. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 19119\u201319129 (2025)","DOI":"10.1109\/ICCV51701.2025.01777"},{"key":"27_CR69","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":"27_CR70","doi-asserted-by":"crossref","unstructured":"Shaocong, D., et al.: From one to more: contextual part latents for 3D generation. In: ICCV (2025)","DOI":"10.1109\/ICCV51701.2025.00771"},{"key":"27_CR71","doi-asserted-by":"publisher","unstructured":"Song, G., Zhao, Z., Weng, H., Zeng, J., Jia, R., Gao, S.: Mesh SILKSONG: auto-regressive mesh generation as weaving silk (2025). https:\/\/doi.org\/10.48550\/arXiv.2507.02477","DOI":"10.48550\/arXiv.2507.02477"},{"key":"27_CR72","doi-asserted-by":"publisher","unstructured":"Tang, G., Zhao, W., Ford, L., Benhaim, D., Zhang, P.: Segment any mesh (2025). https:\/\/doi.org\/10.48550\/arXiv.2408.13679","DOI":"10.48550\/arXiv.2408.13679"},{"key":"27_CR73","doi-asserted-by":"publisher","unstructured":"Tang, J., et al.: Efficient part-level 3D object generation via dual volume packing (2025). https:\/\/doi.org\/10.48550\/arXiv.2506.09980","DOI":"10.48550\/arXiv.2506.09980"},{"key":"27_CR74","unstructured":"Team, T.H.: Hunyuan3D 1.0: a unified framework for text-to-3D and image-to-3D generation (2024)"},{"key":"27_CR75","unstructured":"Team, T.H.: Hunyuan3D 2.0: scaling diffusion models for high resolution textured 3D assets generation (2025)"},{"key":"27_CR76","unstructured":"Team, T.H.: Hunyuan3D 2.5: towards high-fidelity 3D assets generation with ultimate details (2025). https:\/\/arxiv.org\/abs\/2506.16504"},{"key":"27_CR77","unstructured":"Team, T.H.: Hunyuan3D-omni: a unified framework for controllable generation of 3d assets (2025). https:\/\/arxiv.org\/abs\/2509.21245"},{"key":"27_CR78","unstructured":"Wang, J., et al.: Taming rectified flow for inversion and editing. In: Proceedings of the 42nd International Conference on Machine Learning, pp. 64044\u201364058. PMLR (2025)"},{"key":"27_CR79","doi-asserted-by":"crossref","unstructured":"Wang, R., et al.: MOGE: unlocking accurate monocular geometry estimation for open-domain images with optimal training supervision. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 5261\u20135271 (2025)","DOI":"10.1109\/CVPR52734.2025.00496"},{"issue":"4","key":"27_CR80","doi-asserted-by":"publisher","first-page":"600","DOI":"10.1109\/TIP.2003.819861","volume":"13","author":"Z Wang","year":"2004","unstructured":"Wang, Z., Bovik, A., Sheikh, H., Simoncelli, E.: Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13(4), 600\u2013612 (2004). https:\/\/doi.org\/10.1109\/TIP.2003.819861","journal-title":"IEEE Trans. Image Process."},{"key":"27_CR81","doi-asserted-by":"publisher","unstructured":"Wei, S.T., Wang, R.H., Zhou, C.Z., Chen, B., Wang, P.S.: OctGPT: octree-based multiscale autoregressive models for 3D shape generation. In: Proceedings of the Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers, pp. 1\u201311. ACM, Vancouver BC Canada (2025). https:\/\/doi.org\/10.1145\/3721238.3730601","DOI":"10.1145\/3721238.3730601"},{"key":"27_CR82","unstructured":"Wu, C., et al.: Qwen-image technical report (2025). https:\/\/arxiv.org\/abs\/2508.02324"},{"key":"27_CR83","doi-asserted-by":"publisher","unstructured":"Wu, S., et al.: Direct3d-s2: Gigascale 3D generation made easy with spatial sparse attention (2025). https:\/\/doi.org\/10.48550\/arXiv.2505.17412","DOI":"10.48550\/arXiv.2505.17412"},{"key":"27_CR84","doi-asserted-by":"publisher","unstructured":"Wu, T., Zheng, C., Guan, F., Vedaldi, A., Cham, T.J.: Amodal3r: Amodal 3D reconstruction from occluded 2D images (2025). https:\/\/doi.org\/10.48550\/arXiv.2503.13439","DOI":"10.48550\/arXiv.2503.13439"},{"key":"27_CR85","doi-asserted-by":"publisher","unstructured":"Xia, R., Tang, Y., Zhou, P.: Towards scalable and consistent 3D editing 2025). https:\/\/doi.org\/10.48550\/arXiv.2510.02994","DOI":"10.48550\/arXiv.2510.02994"},{"key":"27_CR86","doi-asserted-by":"crossref","unstructured":"Xiang, J., et al.: Structured 3D latents for scalable and versatile 3D generation. arXiv preprint arXiv:2412.01506 (2024)","DOI":"10.1109\/CVPR52734.2025.02000"},{"key":"27_CR87","doi-asserted-by":"publisher","unstructured":"Xu, Y., et al.: GRM: large gaussian reconstruction model for\u00a0efficient 3D reconstruction and\u00a0generation. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds.) Computer Vision \u2013 ECCV 2024, pp. 1\u201320. Springer Nature Switzerland, Cham (2025). https:\/\/doi.org\/10.1007\/978-3-031-72633-0_1","DOI":"10.1007\/978-3-031-72633-0_1"},{"key":"27_CR88","doi-asserted-by":"crossref","unstructured":"Xu, Y., Zhu, L., Yang, Y.: GG-editor: locally editing 3D avatars with multimodal large language model guidance. In: ACM Multimedia 2024 (2024)","DOI":"10.1145\/3664647.3681039"},{"key":"27_CR89","unstructured":"Yan, X., et\u00a0al.: X-part: high fidelity and structure coherent shape decomposition. arXiv preprint arXiv:2509.08643 (2025)"},{"key":"27_CR90","doi-asserted-by":"publisher","unstructured":"Yan, Z., et al.: 3dSceneEditor: controllable 3D scene editing with gaussian splatting (2024).https:\/\/doi.org\/10.48550\/arXiv.2412.01583","DOI":"10.48550\/arXiv.2412.01583"},{"key":"27_CR91","doi-asserted-by":"publisher","unstructured":"Yang, Y., et al.: HoloPart: generative 3D part amodal segmentation (2025). https:\/\/doi.org\/10.48550\/arXiv.2504.07943","DOI":"10.48550\/arXiv.2504.07943"},{"key":"27_CR92","unstructured":"Yang, Y., et al.: Sampart3D: segment any part in 3D objects. arXiv preprint arXiv:2411.07184 (2024)"},{"key":"27_CR93","doi-asserted-by":"publisher","unstructured":"Yang, Y., et al.: OmniPart: part-aware 3D generation with semantic decoupling and structural cohesion (2025). https:\/\/doi.org\/10.48550\/arXiv.2507.06165","DOI":"10.48550\/arXiv.2507.06165"},{"issue":"4","key":"27_CR94","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3730841","volume":"44","author":"K Yao","year":"2025","unstructured":"Yao, K., et al.: Cast: component-aligned 3D scene reconstruction from an RGB image. ACM Trans. Graph. 44(4), 1\u201319 (2025). https:\/\/doi.org\/10.1145\/3730841","journal-title":"ACM Trans. Graph."},{"key":"27_CR95","doi-asserted-by":"publisher","unstructured":"Ye, J., et al.: PrimitiveAnything: human-crafted 3D primitive assembly generation with auto-regressive transformer. In: Proceedings of the Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers, pp. 1\u201312. ACM, Vancouver BC Canada (2025). https:\/\/doi.org\/10.1145\/3721238.3730732","DOI":"10.1145\/3721238.3730732"},{"key":"27_CR96","doi-asserted-by":"publisher","unstructured":"Ye, J., et al.: Nano3D: a training-free approach for efficient 3D editing without masks (2025). https:\/\/doi.org\/10.48550\/arXiv.2510.15019","DOI":"10.48550\/arXiv.2510.15019"},{"key":"27_CR97","unstructured":"Yin, Y., Fu, Z., Yang, F., Lin, G.: Or-NERF: object removing from 3D scenes guided by multiview segmentation with neural radiance fields (2023). https:\/\/arxiv.org\/abs\/2305.10503"},{"key":"27_CR98","doi-asserted-by":"crossref","unstructured":"Yu, Z., Chen, A., Huang, B., Sattler, T., Geiger, A.: MIP-splatting: alias-free 3D gaussian splatting. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19447\u201319456 (2024)","DOI":"10.1109\/CVPR52733.2024.01839"},{"key":"27_CR99","doi-asserted-by":"publisher","unstructured":"Zhang, B., Tang, J., Nie\u00dfner, M., Wonka, P.: 3DSHAPE2VECSET: a 3D shape representation for neural fields and generative diffusion models. ACM Trans. Graph. 42(4), 92:1\u201392:16 (2023). https:\/\/doi.org\/10.1145\/3592442","DOI":"10.1145\/3592442"},{"key":"27_CR100","doi-asserted-by":"publisher","unstructured":"Zhang, R., Isola, P., Efros, A.A., Shechtman, E., Wang, O.: The unreasonable effectiveness of deep features as a perceptual metric. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 586\u2013595 (2018). https:\/\/doi.org\/10.1109\/CVPR.2018.00068","DOI":"10.1109\/CVPR.2018.00068"},{"key":"27_CR101","doi-asserted-by":"publisher","unstructured":"Zhang, X., Lee, J., Joslin, C., Lee, W.: Advancing 3D gaussian splatting editing with complementary and consensus information (2025). https:\/\/doi.org\/10.48550\/arXiv.2503.11601","DOI":"10.48550\/arXiv.2503.11601"},{"key":"27_CR102","doi-asserted-by":"publisher","unstructured":"Zhang, Y., Zhang, L., Ma, R., Cao, N.: TexVerse: a universe of 3d objects with high-resolution textures (2025). https:\/\/doi.org\/10.48550\/arXiv.2508.10868","DOI":"10.48550\/arXiv.2508.10868"},{"key":"27_CR103","doi-asserted-by":"publisher","unstructured":"Zhang, Z., Xie, J., Lu, Y., Yang, Z., Yang, Y.: In-context edit: enabling instructional image editing with in-context generation in large scale diffusion transformer (2025). https:\/\/doi.org\/10.48550\/arXiv.2504.20690","DOI":"10.48550\/arXiv.2504.20690"},{"key":"27_CR104","doi-asserted-by":"publisher","unstructured":"Zhao, W., Cao, Y.P., Xu, J., Dong, Y., Shan, Y.: Assembler: scalable 3D part assembly via anchor point diffusion (2025). https:\/\/doi.org\/10.48550\/arXiv.2506.17074","DOI":"10.48550\/arXiv.2506.17074"},{"key":"27_CR105","doi-asserted-by":"publisher","unstructured":"Zheng, K., Zha, R., Xu, Z., Gu, J., Yang, J., Wang, X.E.: Constructing a 3D scene from a single image (2025). https:\/\/doi.org\/10.48550\/arXiv.2505.15765","DOI":"10.48550\/arXiv.2505.15765"},{"key":"27_CR106","doi-asserted-by":"publisher","unstructured":"Zhou, Z., Deng, Y., He, X., Dong, W., Tang, F.: Multi-turn consistent image editing (2025). https:\/\/doi.org\/10.48550\/arXiv.2505.04320","DOI":"10.48550\/arXiv.2505.04320"},{"key":"27_CR107","unstructured":"Zhu, Z., et al.: PartSam: a scalable promptable part segmentation model trained on native 3D data. arXiv preprint arXiv:2509.21965 (2025)"},{"issue":"4","key":"27_CR108","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3658205","volume":"43","author":"J Zhuang","year":"2024","unstructured":"Zhuang, J., Kang, D., Cao, Y.P., Li, G., Lin, L., Shan, Y.: Tip-editor: an accurate 3D editor following both text-prompts and image-prompts. ACM Trans. Graph. 43(4), 1\u201312 (2024). https:\/\/doi.org\/10.1145\/3658205","journal-title":"ACM Trans. Graph."}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-36839-3_27","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,13]],"date-time":"2026-09-13T16:26:32Z","timestamp":1789316792000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-36839-3_27"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032368386","9783032368393"],"references-count":108,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-36839-3_27","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":"14 September 2026","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":"Malm\u00f6","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sweden","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}