{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T10:06:37Z","timestamp":1789207597503,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":47,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032373342","type":"print"},{"value":"9783032373359","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\/978-3-032-37335-9_31","type":"book-chapter","created":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T09:14:58Z","timestamp":1789204498000},"page":"567-585","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["SIMON: SImultaneous Multi-object Navigation"],"prefix":"10.1007","author":[{"given":"Yifeng","family":"Zhu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Siyuan","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Bao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Buyu","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,13]]},"reference":[{"issue":"5","key":"31_CR1","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3750722","volume":"44","author":"H Alzayer","year":"2025","unstructured":"Alzayer, H., Xia, Z., Zhang, X., Shechtman, E., Huang, J.B., Gharbi, M.: Magic fixup: streamlining photo editing by watching dynamic videos. ACM Trans. Graph. 44(5), 1\u201325 (2025)","journal-title":"ACM Trans. Graph."},{"key":"31_CR2","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":"31_CR3","first-page":"8780","volume":"34","author":"P Dhariwal","year":"2021","unstructured":"Dhariwal, P., Nichol, A.: Diffusion models beat GANs on image synthesis. Adv. Neural. Inf. Process. Syst. 34, 8780\u20138794 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"31_CR4","doi-asserted-by":"crossref","unstructured":"Duan, Z.P., et al.: A diffusion-based framework for occluded object movement. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 39, pp. 2816\u20132824 (2025)","DOI":"10.1609\/aaai.v39i3.32287"},{"key":"31_CR5","doi-asserted-by":"crossref","unstructured":"Fu, H., et al.: 3D-FUTURE: 3D Furniture shape with texture (2020). arxiv preprint arxiv: 2009.09633","DOI":"10.1007\/s11263-021-01534-z"},{"key":"31_CR6","doi-asserted-by":"crossref","unstructured":"Gatys, L.A., Ecker, A.S., Bethge, M.: Image style transfer using convolutional neural networks. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2414\u20132423 (2016)","DOI":"10.1109\/CVPR.2016.265"},{"key":"31_CR7","unstructured":"Goodfellow, I.J., et al.: Generative adversarial nets. In: Advances in Neural Information Processing Systems, pp. 2672\u20132680 (2014)"},{"key":"31_CR8","doi-asserted-by":"crossref","unstructured":"Han, L., et\u00a0al.: Proxedit: Improving tuning-free real image editing with proximal guidance. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 4291\u20134301 (2024)","DOI":"10.1109\/WACV57701.2024.00424"},{"key":"31_CR9","unstructured":"Hertz, A., Mokady, R., Tenenbaum, J., Aberman, K., Pritch, Y., Cohen-Or, D.: Prompt-to-prompt image editing with cross attention control. In: International Conference on Learning Representations (2022)"},{"key":"31_CR10","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, vol. 30 (2017)"},{"key":"31_CR11","first-page":"6840","volume":"33","author":"J Ho","year":"2020","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. Adv. Neural. Inf. Process. Syst. 33, 6840\u20136851 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"31_CR12","doi-asserted-by":"crossref","unstructured":"Isola, P., Zhu, J.Y., Zhou, T., Efros, A.A.: Image-to-image translation with conditional adversarial networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 1125\u20131134 (2017)","DOI":"10.1109\/CVPR.2017.632"},{"key":"31_CR13","doi-asserted-by":"crossref","unstructured":"Jiang, R., Fu, X., Zheng, G., Li, T., Yao, T., Li, X.: Energy-guided optimization for personalized image editing with pretrained text-to-image diffusion models. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a039, pp. 4048\u20134056 (2025)","DOI":"10.1609\/aaai.v39i4.32424"},{"key":"31_CR14","unstructured":"Karras, T., Aila, T., Laine, S., Lehtinen, J.: Progressive growing of GANs for improved quality, stability, and variation. In: International Conference on Learning Representations (2018)"},{"key":"31_CR15","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., Aila, T.: A style-based generator architecture for generative adversarial networks. In: Proceedings of the IEEE\/CVF Conference On Computer Vision and Pattern Recognition, pp. 4401\u20134410 (2019)","DOI":"10.1109\/CVPR.2019.00453"},{"key":"31_CR16","doi-asserted-by":"crossref","unstructured":"Kim, G., Kwon, T., Ye, J.C.: DiffusionCLIP: text-guided diffusion models for robust image manipulation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2426\u20132435 (2022)","DOI":"10.1109\/CVPR52688.2022.00246"},{"key":"31_CR17","unstructured":"Kirillov, A., et al.: Proceedings of the IEEE\/CVF international conference on computer vision, pp. 4015\u20134026 (2023). Segment anything"},{"key":"31_CR18","unstructured":"Labs, B.F.: Flux (2024)"},{"key":"31_CR19","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: GLIGEN: open-set grounded text-to-image generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 22511\u201322521 (2023)","DOI":"10.1109\/CVPR52729.2023.02156"},{"key":"31_CR20","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., et al.: Microsoft coco: common objects in context. In: Computer Vision\u2013ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, proceedings, part v 13, pp. 740\u2013755. Springer (2014)","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"31_CR21","doi-asserted-by":"crossref","unstructured":"Liu, C., Li, X., Ding, H.: Referring image editing: object-level image editing via referring expressions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13128\u201313138 (2024)","DOI":"10.1109\/CVPR52733.2024.01247"},{"key":"31_CR22","doi-asserted-by":"crossref","unstructured":"Lugmayr, A., Danelljan, M., Romero, A., Yu, F., Timofte, R., Van Gool, L.: Repaint: inpainting using denoising diffusion probabilistic models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11461\u201311471 (2022)","DOI":"10.1109\/CVPR52688.2022.01117"},{"issue":"1","key":"31_CR23","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"},{"key":"31_CR24","doi-asserted-by":"crossref","unstructured":"Mou, C., Wang, X., Song, J., Shan, Y., Zhang, J.: DiffEditor: boosting accuracy and flexibility on diffusion-based image editing. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8488\u20138497 (2024)","DOI":"10.1109\/CVPR52733.2024.00811"},{"key":"31_CR25","unstructured":"Mou, C., Wang, X., Song, J., Shan, Y., Zhang, J.: Dragondiffusion: Enabling drag-style manipulation on diffusion models. In: Proceedings of the International Conference on Learning Representations (2024)"},{"key":"31_CR26","unstructured":"Nichol, A.Q., et al.: Glide: towards photorealistic image generation and editing with text-guided diffusion models. In: International Conference on Machine Learning, pp. 16784\u201316804. PMLR (2022)"},{"key":"31_CR27","unstructured":"Oquab, M., et al.: DINOv2: learning robust visual features without supervision, (2023). arXiv preprint arXiv:2304.07193"},{"key":"31_CR28","doi-asserted-by":"crossref","unstructured":"Pan, X., Tewari, A., Leimk\u00fchler, T., Liu, L., Meka, A., Theobalt, C.: Drag your GAN: interactive point-based manipulation on the generative image manifold. In: ACM SIGGRAPH 2023 Conference Proceedings, pp. 1\u201311 (2023)","DOI":"10.1145\/3588432.3591500"},{"key":"31_CR29","doi-asserted-by":"crossref","unstructured":"Pathak, D., Krahenbuhl, P., Donahue, J., Darrell, T., Efros, A.A.: Context encoders: feature learning by inpainting. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2536\u20132544 (2016)","DOI":"10.1109\/CVPR.2016.278"},{"key":"31_CR30","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PmLR (2021)"},{"key":"31_CR31","doi-asserted-by":"crossref","unstructured":"Ren, J., Xu, M., Wu, J.C., Liu, Z., Xiang, T., Toisoul, A.: Move anything with layered scene diffusion. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6380\u20136389 (2024)","DOI":"10.1109\/CVPR52733.2024.00610"},{"key":"31_CR32","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, pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"31_CR33","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":"31_CR34","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), pp. 472\u2013482. IEEE (2025)","DOI":"10.1109\/WACV61041.2025.00056"},{"key":"31_CR35","doi-asserted-by":"crossref","unstructured":"Sauer, A., Schwarz, K., Geiger, A.: StyleGAN-XL: scaling styleGAN to large diverse datasets. In: ACM SIGGRAPH 2022 conference proceedings, pp. 1\u201310 (2022)","DOI":"10.1145\/3528233.3530738"},{"key":"31_CR36","doi-asserted-by":"crossref","unstructured":"Shi, Y., et al.: DragDiffusion: harnessing diffusion models for interactive point-based image editing. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8839\u20138849 (2024)","DOI":"10.1109\/CVPR52733.2024.00844"},{"key":"31_CR37","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models (2020). arXiv preprint arXiv:2010.02502"},{"key":"31_CR38","doi-asserted-by":"crossref","unstructured":"Song, W., Jiang, H., Yang, Z., Quan, R., Yang, Y.: Insert anything: image insertion via in-context editing in dit. arXiv preprint arXiv:2504.15009 (2025)","DOI":"10.1609\/aaai.v40i11.37866"},{"key":"31_CR39","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":"31_CR40","doi-asserted-by":"crossref","unstructured":"Wang, X., Darrell, T., Rambhatla, S.S., Girdhar, R., Misra, I.: InstanceDiffusion: instance-level control for image generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6232\u20136242 (2024)","DOI":"10.1109\/CVPR52733.2024.00596"},{"key":"31_CR41","doi-asserted-by":"crossref","unstructured":"Xie, J., Li, Y., Huang, Y., Liu, H., Zhang, W., Zheng, Y., Shou, M.Z.: BoxDiff: text-to-image synthesis with training-free box-constrained diffusion. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7452\u20137461 (2023)","DOI":"10.1109\/ICCV51070.2023.00685"},{"key":"31_CR42","doi-asserted-by":"crossref","unstructured":"Yu, X., Wang, T., Kim, S.Y., Guerrero, P., Chen, X., Liu, Q., Lin, Z., Qi, X.: ObjectMover: generative object movement with video prior. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 17682\u201317691 (2025)","DOI":"10.1109\/CVPR52734.2025.01647"},{"key":"31_CR43","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, pp. 3836\u20133847 (2023)","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"31_CR44","unstructured":"Zhang, L., Rao, A., Agrawala, M.: Scaling in-the-wild training for diffusion-based illumination harmonization and editing by imposing consistent light transport. In: The Thirteenth International Conference on Learning Representations (2025)"},{"key":"31_CR45","doi-asserted-by":"crossref","unstructured":"Zhang, R., Isola, P., Efros, A.A., Shechtman, E., Wang, O.: The unreasonable effectiveness of deep features as a perceptual metric. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 586\u2013595. (2018)","DOI":"10.1109\/CVPR.2018.00068"},{"key":"31_CR46","doi-asserted-by":"crossref","unstructured":"Zheng, G., Zhou, X., Li, X., Qi, Z., Shan, Y., Li, X.: Layoutdiffusion: Controllable diffusion model for layout-to-image generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 22490\u201322499 (2023)","DOI":"10.1109\/CVPR52729.2023.02154"},{"key":"31_CR47","doi-asserted-by":"crossref","unstructured":"Zhou, S., Xiao, T., Yang, Y., Feng, D., He, Q., He, W.: Genegan: Learning object transfiguration and attribute subspace from unpaired data. In: Proceedings of the British Machine Vision Conference (BMVC) (2017)","DOI":"10.5244\/C.31.111"}],"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\/978-3-032-37335-9_31","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T09:15:11Z","timestamp":1789204511000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37335-9_31"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032373342","9783032373359"],"references-count":47,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37335-9_31","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":"13 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"}}]}}