{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T19:59:11Z","timestamp":1790279951399,"version":"4.1.0"},"publisher-location":"Cham","reference-count":57,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032369833","type":"print"},{"value":"9783032369840","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\/978-3-032-36984-0_19","type":"book-chapter","created":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T19:05:06Z","timestamp":1790276706000},"page":"341-359","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["BlenderFusion: 3D-Grounded Visual Editing and\u00a0Generative Compositing"],"prefix":"10.1007","author":[{"given":"Jiacheng","family":"Chen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ramin","family":"Mehran","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuhui","family":"Jia","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Saining","family":"Xie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sanghyun","family":"Woo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,25]]},"reference":[{"key":"19_CR1","doi-asserted-by":"crossref","unstructured":"Ahmadyan, A., Zhang, L., Ablavatski, A., Wei, J., Grundmann, M.: Objectron: a large scale dataset of object-centric videos in the wild with pose annotations. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2021)","DOI":"10.1109\/CVPR46437.2021.00773"},{"key":"19_CR2","doi-asserted-by":"crossref","unstructured":"Alzayer, H., Xia, Z., Zhang, X., Shechtman, E., Huang, J.B., Gharbi, M.: Magic fixup: streamlining photo editing by watching dynamic videos. arXiv preprint arXiv:2403.13044 (2024)","DOI":"10.1145\/3750722"},{"key":"19_CR3","unstructured":"Baldridge, J., et al.: Imagen 3. arXiv preprint arXiv:2408.07009 (2024)"},{"key":"19_CR4","unstructured":"Baruch, G., et al.: ArkitScenes: a diverse real-world dataset for 3D indoor scene understanding using mobile RGB-D data. arXiv preprint arXiv:2111.08897 (2021)"},{"key":"19_CR5","unstructured":"Bochkovskii, A., et al.: Depth pro: sharp monocular metric depth in less than a second. arXiv preprint arXiv:2410.02073 (2024)"},{"key":"19_CR6","doi-asserted-by":"crossref","unstructured":"Chen, W., et al.: Subject-driven text-to-image generation via apprenticeship learning. In: Advances in Neural Information Processing Systems (NeurIPS) (2023)","DOI":"10.52202\/075280-1318"},{"key":"19_CR7","unstructured":"Chen, W., Hu, H., Saharia, C., Cohen, W.W.: Re-imagen: retrieval-augmented text-to-image generator. arXiv preprint arXiv:2209.14491 (2022)"},{"key":"19_CR8","doi-asserted-by":"crossref","unstructured":"Chen, X., Huang, L., Liu, Y., Shen, Y., Zhao, D., Zhao, H.: Anydoor: zero-shot object-level image customization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2024)","DOI":"10.1109\/CVPR52733.2024.00630"},{"key":"19_CR9","doi-asserted-by":"crossref","unstructured":"Cheng, Y.C., et al.: 3D-fixup: advancing photo editing with 3D priors. arXiv preprint arXiv:2505.10566 (2025)","DOI":"10.1145\/3721238.3730695"},{"key":"19_CR10","doi-asserted-by":"crossref","unstructured":"Gao, R., et al.: Cat3D: create anything in 3D with multi-view diffusion models. arXiv preprint arXiv:2405.10314 (2024)","DOI":"10.52202\/079017-2403"},{"key":"19_CR11","doi-asserted-by":"crossref","unstructured":"Garibi, D., et al.: TokenVerse: versatile multi-concept personalization in token modulation space. arXiv preprint arXiv:2501.12224 (2025)","DOI":"10.1145\/3730843"},{"key":"19_CR12","unstructured":"Greff, K., et\u00a0al.: Kubric: a scalable dataset generator. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2022)"},{"key":"19_CR13","doi-asserted-by":"crossref","unstructured":"Gu, Y., Huang, I., Je, J., Yang, G., Guibas, L.: BlenderGym: benchmarking foundational model systems for graphics editing. arXiv preprint arXiv:2504.01786 (2025)","DOI":"10.1109\/CVPR52734.2025.01731"},{"key":"19_CR14","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV) (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"19_CR15","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. In: Advances in Neural Information Processing Systems (NeurIPS) (2020)"},{"key":"19_CR16","unstructured":"Ho, J., Salimans, T.: Classifier-free diffusion guidance. arXiv preprint arXiv:2207.12598 (2022)"},{"key":"19_CR17","doi-asserted-by":"crossref","unstructured":"Hu, H., et al.: Instruct-imagen: image generation with multi-modal instruction. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.00455"},{"key":"19_CR18","unstructured":"Hu, Z., et al.: SceneCraft: an LLM agent for synthesizing 3D scenes as blender code. In: Forty-First International Conference on Machine Learning (ICML) (2024)"},{"key":"19_CR19","doi-asserted-by":"crossref","unstructured":"Huang, I., et al.: Fireplace: geometric refinements of LLM common sense reasoning for 3D object placement. In: Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR) (2025)","DOI":"10.1109\/CVPR52734.2025.01257"},{"key":"19_CR20","doi-asserted-by":"crossref","unstructured":"Huang, I., Yang, G., Guibas, L.: BlenderAlchemy: editing 3D graphics with vision-language models. In: European Conference on Computer Vision (ECCV) (2024)","DOI":"10.1007\/978-3-031-73024-5_18"},{"key":"19_CR21","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., Aittala, M., Hellsten, J., Lehtinen, J., Aila, T.: Analyzing and improving the image quality of styleGAN. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"19_CR22","doi-asserted-by":"crossref","unstructured":"Leroy, V., Cabon, Y., Revaud, J.: Grounding image matching in 3D with MASt3R. In: European Conference on Computer Vision (2024)","DOI":"10.1007\/978-3-031-73220-1_5"},{"key":"19_CR23","doi-asserted-by":"crossref","unstructured":"Liu, R., Wu, R., Van Hoorick, 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 (2023)","DOI":"10.1109\/ICCV51070.2023.00853"},{"key":"19_CR24","doi-asserted-by":"crossref","unstructured":"Liu, S., et\u00a0al.: Grounding DINO: marrying DINO with grounded pre-training for open-set object detection. In: European Conference on Computer Vision (ECCV). Springer (2024)","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"19_CR25","doi-asserted-by":"crossref","unstructured":"Lu, S., Liu, Y., Kong, A.W.K.: TF-icon: diffusion-based training-free cross-domain image composition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2023)","DOI":"10.1109\/ICCV51070.2023.00218"},{"key":"19_CR26","doi-asserted-by":"crossref","unstructured":"Michel, O., Bhattad, A., VanderBilt, E., Krishna, R., Kembhavi, A., Gupta, T.: Object 3DiT: language-guided 3D-aware image editing. Advances in Neural Information Processing Systems (NeurIPS) (2024)","DOI":"10.52202\/075280-0155"},{"key":"19_CR27","doi-asserted-by":"crossref","unstructured":"Pandey, K., et al.: Diffusion handles enabling 3D edits for diffusion models by lifting activations to 3D. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2024)","DOI":"10.1109\/CVPR52733.2024.00735"},{"key":"19_CR28","doi-asserted-by":"crossref","unstructured":"Peebles, W., Xie, S.: Scalable diffusion models with transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2023)","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"19_CR29","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning (ICML) (2021)"},{"key":"19_CR30","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":"19_CR31","unstructured":"Ravi, N., et\u00a0al.: SAM 2: segment anything in images and videos. arXiv preprint arXiv:2408.00714 (2024)"},{"key":"19_CR32","doi-asserted-by":"crossref","unstructured":"Roberts, M., et al.: HyperSim: a photorealistic synthetic dataset for holistic indoor scene understanding. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2021)","DOI":"10.1109\/ICCV48922.2021.01073"},{"key":"19_CR33","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":"19_CR34","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 (CVPR) (2023)","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"19_CR35","doi-asserted-by":"crossref","unstructured":"Saharia, C., et al.: Photorealistic text-to-image diffusion models with deep language understanding. In: Advances in Neural Information Processing Systems (NeurIPS) (2022)","DOI":"10.52202\/068431-2643"},{"key":"19_CR36","doi-asserted-by":"crossref","unstructured":"Sajnani, R., Vanbaar, J., Min, J., Katyal, K., Sridhar, S.: GeoDiffuser: geometry-based image editing with diffusion models. In: 2025 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV) (2025)","DOI":"10.1109\/WACV61041.2025.00056"},{"key":"19_CR37","unstructured":"Shi, Y., Wang, P., Ye, J., Long, M., Li, K., Yang, X.: MVDream: multi-view diffusion for 3D generation. arXiv preprint arXiv:2308.16512 (2023)"},{"key":"19_CR38","unstructured":"Sitzmann, V., Rezchikov, S., Freeman, B., Tenenbaum, J., Durand, F.: Light field networks: neural scene representations with single-evaluation rendering. In: Advances in Neural Information Processing Systems (NeurIPS) (2021)"},{"key":"19_CR39","unstructured":"Sohl-Dickstein, J., Weiss, E., Maheswaranathan, N., Ganguli, S.: Deep unsupervised learning using nonequilibrium thermodynamics. In: International Conference on Machine Learning (ICML) (2015)"},{"key":"19_CR40","doi-asserted-by":"crossref","unstructured":"Sohn, K., et al.: StyleDrop: text-to-image generation in any style. arXiv preprint arXiv:2306.00983 (2023)","DOI":"10.52202\/075280-2920"},{"key":"19_CR41","doi-asserted-by":"crossref","unstructured":"Song, S., Lichtenberg, S.P., Xiao, J.: Sun RGB-D: a RGB-D scene understanding benchmark suite. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2015)","DOI":"10.1109\/CVPR.2015.7298655"},{"key":"19_CR42","unstructured":"Song, Y., Sohl-Dickstein, J., Kingma, D.P., Kumar, A., Ermon, S., Poole, B.: Score-based generative modeling through stochastic differential equations. arXiv preprint arXiv:2011.13456 (2020)"},{"key":"19_CR43","unstructured":"Song, Y., et al.: ObjectStitch: generative object compositing. arXiv preprint arXiv:2212.00932 (2022)"},{"key":"19_CR44","doi-asserted-by":"crossref","unstructured":"Song, Y., et al.: Imprint: generative object compositing by learning identity-preserving representation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2024)","DOI":"10.1109\/CVPR52733.2024.00769"},{"key":"19_CR45","doi-asserted-by":"crossref","unstructured":"Sun, P., et al.: Scalability in perception for autonomous driving: waymo open dataset. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00252"},{"key":"19_CR46","doi-asserted-by":"crossref","unstructured":"Tang, S., et al.: MVDiffusion++: a dense high-resolution multi-view diffusion model for single or sparse-view 3D object reconstruction. In: European Conference on Computer Vision (ECCV) (2024)","DOI":"10.1007\/978-3-031-72640-8_10"},{"key":"19_CR47","doi-asserted-by":"crossref","unstructured":"Tarr\u00e9s, G.C., et al.: Multitwine: multi-object compositing with text and layout control. arXiv preprint arXiv:2502.05165 (2025)","DOI":"10.1109\/CVPR52734.2025.00758"},{"key":"19_CR48","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in neural information processing systems (NeurIPS) (2017)"},{"key":"19_CR49","doi-asserted-by":"crossref","unstructured":"Wang, J., Chen, M., Karaev, N., Vedaldi, A., Rupprecht, C., Novotny, D.: VGGT: visual geometry grounded transformer. arXiv preprint arXiv:2503.11651 (2025)","DOI":"10.1109\/CVPR52734.2025.00499"},{"key":"19_CR50","doi-asserted-by":"crossref","unstructured":"Wang, S., Leroy, V., Cabon, Y., Chidlovskii, B., Revaud, J.: DUSt3R: geometric 3D vision made easy. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), (2024)","DOI":"10.1109\/CVPR52733.2024.01956"},{"key":"19_CR51","doi-asserted-by":"crossref","unstructured":"Wu, Z., et al.: Neural assets: 3D-aware multi-object scene synthesis with image diffusion models. In: Advances in Neural Information Processing Systems (NeurIPS) (2024)","DOI":"10.52202\/079017-2429"},{"key":"19_CR52","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":"19_CR53","doi-asserted-by":"crossref","unstructured":"Yenphraphai, J., Pan, X., Liu, S., Panozzo, D., Xie, S.: Image sculpting: precise object editing with 3D geometry control. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2024)","DOI":"10.1109\/CVPR52733.2024.00406"},{"key":"19_CR54","doi-asserted-by":"crossref","unstructured":"Yuan, Z., Cao, M., Wang, X., Qi, Z., Yuan, C., Shan, Y.: CustomNet: zero-shot object customization with variable-viewpoints in text-to-image diffusion models. arXiv preprint arXiv:2310.19784 (2023)","DOI":"10.1145\/3664647.3681396"},{"key":"19_CR55","unstructured":"Zhang, B., et al.: ControlCom: controllable image composition using diffusion model. arXiv preprint arXiv:2308.10040 (2023)"},{"key":"19_CR56","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) (2023)","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"19_CR57","unstructured":"Zhao, Z., et\u00a0al.: Hunyuan3D 2.0: scaling diffusion models for high resolution textured 3D assets generation. arXiv preprint arXiv:2501.12202 (2025)"}],"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\/978-3-032-36984-0_19","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T19:05:28Z","timestamp":1790276728000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-36984-0_19"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032369833","9783032369840"],"references-count":57,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-36984-0_19","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":"25 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"}}]}}