{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,25]],"date-time":"2025-05-25T19:10:03Z","timestamp":1748200203038,"version":"3.41.0"},"publisher-location":"Cham","reference-count":81,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031923869","type":"print"},{"value":"9783031923876","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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\/978-3-031-92387-6_24","type":"book-chapter","created":{"date-parts":[[2025,5,25]],"date-time":"2025-05-25T18:42:29Z","timestamp":1748198549000},"page":"339-357","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Collaborative Control for\u00a0Geometry-Conditioned PBR Image Generation"],"prefix":"10.1007","author":[{"given":"Shimon","family":"Vainer","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7515-4934","authenticated-orcid":false,"given":"Mark","family":"Boss","sequence":"additional","affiliation":[]},{"given":"Mathias","family":"Parger","sequence":"additional","affiliation":[]},{"given":"Konstantin","family":"Kutsy","sequence":"additional","affiliation":[]},{"given":"Dante","family":"De Nigris","sequence":"additional","affiliation":[]},{"given":"Ciara","family":"Rowles","sequence":"additional","affiliation":[]},{"given":"Nicolas","family":"Perony","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7461-8589","authenticated-orcid":false,"given":"Simon","family":"Donn\u00e9","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,5,12]]},"reference":[{"key":"24_CR1","unstructured":"Achiam, J., et al.: GPT-4 technical report. arXiv preprint arXiv:2303.08774 (2023)"},{"key":"24_CR2","first-page":"21","volume":"1050","author":"JL Ba","year":"2016","unstructured":"Ba, J.L., Kiros, J.R., Hinton, G.E.: Layer normalization. Stat 1050, 21 (2016)","journal-title":"Stat"},{"key":"24_CR3","unstructured":"Burley, B.: Physically based shading at disney. In: ACM Transactions on Graphics (SIGGRAPH) (2012)"},{"key":"24_CR4","doi-asserted-by":"crossref","unstructured":"Cao, T., Kreis, K., Fidler, S., Sharp, N., Yin, K.: Texfusion: synthesizing 3D textures with text-guided image diffusion models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4169\u20134181 (2023)","DOI":"10.1109\/ICCV51070.2023.00385"},{"key":"24_CR5","doi-asserted-by":"crossref","unstructured":"Chambon, T., Heitz, E., Belcour, L.: Passing multi-channel material textures to a 3-channel loss. In: ACM SIGGRAPH 2021 Talks, pp.\u00a01\u20132 (2021)","DOI":"10.1145\/3450623.3464685"},{"key":"24_CR6","doi-asserted-by":"crossref","unstructured":"Chen, D.Z., Siddiqui, Y., Lee, H.Y., Tulyakov, S., Nie\u00dfner, M.: Text2tex: text-driven texture synthesis via diffusion models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 18558\u201318568 (2023)","DOI":"10.1109\/ICCV51070.2023.01701"},{"key":"24_CR7","doi-asserted-by":"crossref","unstructured":"Chen, R., Chen, Y., Jiao, N., Jia, K.: Fantasia3d: disentangling geometry and appearance for high-quality text-to-3D content creation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 22246\u201322256 (2023)","DOI":"10.1109\/ICCV51070.2023.02033"},{"key":"24_CR8","doi-asserted-by":"crossref","unstructured":"Cook, R.L., Torrance, K.E.: A reflectance model for computer graphics. ACM Trans. Graph. (ToG) (1982)","DOI":"10.1145\/357290.357293"},{"key":"24_CR9","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":"24_CR10","unstructured":"Denis\u00a0Zavadski, J.F.F., Rother, C.: Controlnet-XS: designing an efficient and effective architecture for controlling text-to-image diffusion models (2023)"},{"key":"24_CR11","unstructured":"Du, X., Kolkin, N., Shakhnarovich, G., Bhattad, A.: Intrinsic LoRA: a generalist approach for discovering knowledge in generative models. In: Synthetic Data for Computer Vision Workshop, CVPR (2024)"},{"key":"24_CR12","doi-asserted-by":"crossref","unstructured":"Duan, Y., Guo, X., Zhu, Z.: Diffusiondepth: diffusion denoising approach for monocular depth estimation. arXiv preprint arXiv:2303.05021 (2023)","DOI":"10.1007\/978-3-031-73247-8_25"},{"key":"24_CR13","unstructured":"Foong, T.Y., Kotyan, S., Mao, P.Y., Vargas, D.V.: The challenges of image generation models in generating multi-component images. arXiv preprint arXiv:2311.13620 (2023)"},{"issue":"11","key":"24_CR14","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1145\/3422622","volume":"63","author":"I Goodfellow","year":"2020","unstructured":"Goodfellow, I., et al.: Generative adversarial networks. Commun. ACM 63(11), 139\u2013144 (2020)","journal-title":"Commun. ACM"},{"key":"24_CR15","unstructured":"Guo, P., et al.: Stabledreamer: taming noisy score distillation sampling for text-to-3D. arXiv preprint arXiv:2312.02189 (2023)"},{"key":"24_CR16","doi-asserted-by":"crossref","unstructured":"Hessel, J., Holtzman, A., Forbes, M., Bras, R.L., Choi, Y.: Clipscore: a reference-free evaluation metric for image captioning. arXiv preprint arXiv:2104.08718 (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"24_CR17","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 (2017)"},{"key":"24_CR18","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":"24_CR19","unstructured":"Hu, E.J., et al.: Lora: low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685 (2021)"},{"key":"24_CR20","doi-asserted-by":"crossref","unstructured":"Hu, L.: Animate anyone: consistent and controllable image-to-video synthesis for character animation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8153\u20138163 (2024)","DOI":"10.1109\/CVPR52733.2024.00779"},{"key":"24_CR21","doi-asserted-by":"crossref","unstructured":"Huang, T., et al.: Dreamcontrol: control-based text-to-3D generation with 3D self-prior. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5364\u20135373 (2024)","DOI":"10.1109\/CVPR52733.2024.00513"},{"key":"24_CR22","unstructured":"Huang, Y., Wang, J., Shi, Y., Qi, X., Zha, Z.J., Zhang, L.: Dreamtime: an improved optimization strategy for text-to-3D content creation. arXiv preprint arXiv:2306.12422 (2023)"},{"key":"24_CR23","doi-asserted-by":"crossref","unstructured":"Jayasumana, S., Ramalingam, S., Veit, A., Glasner, D., Chakrabarti, A., Kumar, S.: Rethinking fid: towards a better evaluation metric for image generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9307\u20139315 (2024)","DOI":"10.1109\/CVPR52733.2024.00889"},{"key":"24_CR24","unstructured":"Jin, Z., Shen, X., Li, B., Xue, X.: Training-free diffusion model adaptation for variable-sized text-to-image synthesis. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"24_CR25","unstructured":"Karras, T., Aila, T., Laine, S., Lehtinen, J.: Progressive growing of GANs for improved quality, stability, and variation. arXiv preprint arXiv:1710.10196 (2017)"},{"key":"24_CR26","first-page":"852","volume":"34","author":"T Karras","year":"2021","unstructured":"Karras, T., et al.: Alias-free generative adversarial networks. Adv. Neural. Inf. Process. Syst. 34, 852\u2013863 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"24_CR27","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":"24_CR28","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, pp. 8110\u20138119 (2020)","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"24_CR29","doi-asserted-by":"crossref","unstructured":"Ke, B., Obukhov, A., Huang, S., Metzger, N., Daudt, R.C., Schindler, K.: Repurposing diffusion-based image generators for monocular depth estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9492\u20139502 (2024)","DOI":"10.1109\/CVPR52733.2024.00907"},{"key":"24_CR30","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114 (2013)"},{"key":"24_CR31","unstructured":"Knodt, J., Gao, X.: Consistent mesh diffusion. arXiv preprint arXiv:2312.00971 (2023)"},{"key":"24_CR32","unstructured":"Le, C., Hetang, C., Cao, A., He, Y.: Euclidreamer: fast and high-quality texturing for 3D models with stable diffusion depth. arXiv preprint arXiv:2311.15573 (2023)"},{"key":"24_CR33","doi-asserted-by":"crossref","unstructured":"Lee, H.Y., Tseng, H.Y., Yang, M.H.: Exploiting diffusion prior for generalizable dense prediction. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7861\u20137871 (2024)","DOI":"10.1109\/CVPR52733.2024.00751"},{"key":"24_CR34","unstructured":"Li, X., et al.: Advances in 3D generation: a survey. arXiv preprint arXiv:2401.17807 (2024)"},{"key":"24_CR35","doi-asserted-by":"crossref","unstructured":"Liang, Y., Yang, X., Lin, J., Li, H., Xu, X., Chen, Y.: Luciddreamer: towards high-fidelity text-to-3D generation via interval score matching. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6517\u20136526 (2024)","DOI":"10.1109\/CVPR52733.2024.00623"},{"key":"24_CR36","doi-asserted-by":"crossref","unstructured":"Lin, S., Liu, B., Li, J., Yang, X.: Common diffusion noise schedules and sample steps are flawed. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 5404\u20135411 (2024)","DOI":"10.1109\/WACV57701.2024.00532"},{"key":"24_CR37","doi-asserted-by":"crossref","unstructured":"Liu, F., Wu, D., Wei, Y., Rao, Y., Duan, Y.: Sherpa3d: boosting high-fidelity text-to-3D generation via coarse 3D prior. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 20763\u201320774 (2024)","DOI":"10.1109\/CVPR52733.2024.01962"},{"key":"24_CR38","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":"24_CR39","doi-asserted-by":"crossref","unstructured":"Liu, Y.T., Guo, Y.C., Luo, G., Sun, H., Yin, W., Zhang, S.H.: Pi3d: efficient text-to-3D generation with pseudo-image diffusion. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19915\u201319924 (2024)","DOI":"10.1109\/CVPR52733.2024.01882"},{"key":"24_CR40","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Unidream: unifying diffusion priors for relightable text-to-3D generation. arXiv preprint arXiv:2312.08754 (2023)","DOI":"10.1007\/978-3-031-72652-1_5"},{"key":"24_CR41","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":"24_CR42","unstructured":"Ma, B., Deng, H., Zhou, J., Liu, Y.S., Huang, T., Wang, X.: Geodream: disentangling 2D and geometric priors for high-fidelity and consistent 3D generation. arXiv preprint arXiv:2311.17971 (2023)"},{"key":"24_CR43","doi-asserted-by":"crossref","unstructured":"Ma, Y., et al.: X-dreamer: creating high-quality 3D content by bridging the domain gap between text-to-2D and text-to-3D generation. arXiv preprint arXiv:2312.00085 (2023)","DOI":"10.1145\/3687475"},{"key":"24_CR44","doi-asserted-by":"crossref","unstructured":"Mou, C., et al.: T2i-adapter: learning adapters to dig out more controllable ability for text-to-image diffusion models. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a038, pp. 4296\u20134304 (2024)","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"24_CR45","unstructured":"Van\u00a0den Oord, A., Kalchbrenner, N., Espeholt, L., Vinyals, O., Graves, A., et\u00a0al.: Conditional image generation with pixelcnn decoders. In: Advances in Neural Information Processing Systems, vol. 29 (2016)"},{"key":"24_CR46","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)"},{"key":"24_CR47","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":"24_CR48","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":"24_CR49","unstructured":"Salimans, T., Goodfellow, I., Zaremba, W., Cheung, V., Radford, A., Chen, X.: Improved techniques for training GANs. In: Advances in Neural Information Processing Systems, vol. 29 (2016)"},{"key":"24_CR50","doi-asserted-by":"crossref","unstructured":"Sarkar, A., Mai, H., Mahapatra, A., Lazebnik, S., Forsyth, D.A., Bhattad, A.: Shadows don\u2019t lie and lines can\u2019t bend! generative models don\u2019t know projective geometry... for now. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 28140\u201328149 (2024)","DOI":"10.1109\/CVPR52733.2024.02658"},{"key":"24_CR51","doi-asserted-by":"publisher","unstructured":"Sartor, S., Peers, P.: Matfusion: a generative diffusion model for SVBRDF capture. In: SIGGRAPH Asia 2023 Conference Papers. SA 2023. ACM (2023). https:\/\/doi.org\/10.1145\/3610548.3618194","DOI":"10.1145\/3610548.3618194"},{"key":"24_CR52","first-page":"25278","volume":"35","author":"C Schuhmann","year":"2022","unstructured":"Schuhmann, C., et al.: LAION-5B: an open large-scale dataset for training next generation image-text models. Adv. Neural. Inf. Process. Syst. 35, 25278\u201325294 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"24_CR53","doi-asserted-by":"crossref","unstructured":"Sharma, P., et al.: Alchemist: parametric control of material properties with diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 24130\u201324141 (2024)","DOI":"10.1109\/CVPR52733.2024.02278"},{"key":"24_CR54","unstructured":"Shi, R., et al.: Zero123++: a single image to consistent multi-view diffusion base model. arXiv preprint arXiv:2310.15110 (2023)"},{"key":"24_CR55","unstructured":"Shi, Y., Wang, P., Ye, J., Mai, L., Li, K., Yang, X.: Mvdream: multi-view diffusion for 3D generation. In: The Twelfth International Conference on Learning Representations (2024)"},{"key":"24_CR56","unstructured":"Sohl-Dickstein, J., Weiss, E., Maheswaranathan, N., Ganguli, S.: Deep unsupervised learning using nonequilibrium thermodynamics. In: International Conference on Machine Learning, pp. 2256\u20132265. PMLR (2015)"},{"key":"24_CR57","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. In: International Conference on Learning Representations (2020)"},{"key":"24_CR58","unstructured":"Stan, G.B.M., et al.: LDM3D: latent diffusion model for 3D. arXiv preprint arXiv:2305.10853 (2023)"},{"key":"24_CR59","doi-asserted-by":"crossref","unstructured":"Subias, J.D., Lagunas, M.: In-the-wild material appearance editing using perceptual attributes. In: Computer Graphics Forum, vol.\u00a042, pp. 333\u2013345. Wiley Online Library (2023)","DOI":"10.1111\/cgf.14765"},{"key":"24_CR60","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2818\u20132826 (2016)","DOI":"10.1109\/CVPR.2016.308"},{"key":"24_CR61","unstructured":"Tang, B., Wang, J., Wu, Z., Zhang, L.: Stable score distillation for high-quality 3D generation. arXiv preprint arXiv:2312.09305 (2023)"},{"key":"24_CR62","unstructured":"Tang, J., Ren, J., Zhou, H., Liu, Z., Zeng, G.: Dreamgaussian: generative gaussian splatting for efficient 3D content creation. In: The Twelfth International Conference on Learning Representations (2024)"},{"key":"24_CR63","unstructured":"https:\/\/huggingface.co\/drhead: Huggingface zerodiffusion model weights v0.9. https:\/\/huggingface.co\/drhead\/ZeroDiffusion. Accessed 08 Feb 2024"},{"key":"24_CR64","unstructured":"Van Den\u00a0Oord, A., Kalchbrenner, N., Kavukcuoglu, K.: Pixel recurrent neural networks. In: International Conference on Machine Learning, pp. 1747\u20131756. PMLR (2016)"},{"key":"24_CR65","unstructured":"Vecchio, G., et al.: Controlmat: a controlled generative approach to material capture. arXiv preprint arXiv:2309.01700 (2023)"},{"key":"24_CR66","unstructured":"Wang, P., et al.: Steindreamer: variance reduction for text-to-3D score distillation via stein identity. arXiv preprint arXiv:2401.00604 (2023)"},{"key":"24_CR67","unstructured":"Wang, Z., Li, M., Chen, C.: Luciddreaming: controllable object-centric 3D generation. arXiv preprint arXiv:2312.00588 (2023)"},{"key":"24_CR68","unstructured":"Wang, Z., et al.: Prolificdreamer: high-fidelity and diverse text-to-3D generation with variational score distillation. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"24_CR69","unstructured":"Wu, H., et al.: Q-align: teaching LMMs for visual scoring via discrete text-defined levels. In: Forty-First International Conference on Machine Learning (2024)"},{"key":"24_CR70","doi-asserted-by":"crossref","unstructured":"Wu, T., et al.: Hyperdreamer: hyper-realistic 3D content generation and editing from a single image. In: SIGGRAPH Asia 2023 Conference Papers, pp. 1\u201310 (2023)","DOI":"10.1145\/3610548.3618168"},{"key":"24_CR71","doi-asserted-by":"crossref","unstructured":"Wu, Z., Zhou, P., Yi, X., Yuan, X., Zhang, H.: Consistent3d: towards consistent high-fidelity text-to-3D generation with deterministic sampling prior. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9892\u20139902 (2024)","DOI":"10.1109\/CVPR52733.2024.00944"},{"key":"24_CR72","unstructured":"Xu, X., Lyu, Z., Pan, X., Dai, B.: Matlaber: material-aware text-to-3D via latent BRDF auto-encoder. arXiv preprint arXiv:2308.09278 (2023)"},{"key":"24_CR73","unstructured":"Ye, H., Zhang, J., Liu, S., Han, X., Yang, W.: IP-adapter: text compatible image prompt adapter for text-to-image diffusion models. arXiv preprint arXiv:2308.06721 (2023)"},{"key":"24_CR74","doi-asserted-by":"crossref","unstructured":"Yeh, Y.Y., et al.: Texturedreamer: image-guided texture synthesis through geometry-aware diffusion. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4304\u20134314 (2024)","DOI":"10.1109\/CVPR52733.2024.00412"},{"key":"24_CR75","doi-asserted-by":"crossref","unstructured":"Youwang, K., Oh, T.H., Pons-Moll, G.: Paint-it: text-to-texture synthesis via deep convolutional texture map optimization and physically-based rendering. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4347\u20134356 (2024)","DOI":"10.1109\/CVPR52733.2024.00416"},{"key":"24_CR76","unstructured":"Yu, K., Liu, J., Feng, M., Cui, M., Xie, X.: Boosting3d: high-fidelity image-to-3D by boosting 2D diffusion prior to 3D prior with progressive learning. arXiv preprint arXiv:2311.13617 (2023)"},{"key":"24_CR77","doi-asserted-by":"crossref","unstructured":"Zeng, X., et al.: Paint3d: paint anything 3D with lighting-less texture diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4252\u20134262 (2024)","DOI":"10.1109\/CVPR52733.2024.00407"},{"key":"24_CR78","doi-asserted-by":"crossref","unstructured":"Zhang, J., et al.: Repaint123: fast and high-quality one image to 3D generation with progressive controllable 2D repainting. arXiv preprint arXiv:2312.13271 (2023)","DOI":"10.1007\/978-3-031-72698-9_18"},{"key":"24_CR79","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":"24_CR80","doi-asserted-by":"crossref","unstructured":"Zhou, L., Shih, A., Meng, C., Ermon, S.: Dreampropeller: supercharge text-to-3D generation with parallel sampling. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4610\u20134619 (2024)","DOI":"10.1109\/CVPR52733.2024.00441"},{"key":"24_CR81","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 Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-92387-6_24","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,25]],"date-time":"2025-05-25T18:42:51Z","timestamp":1748198571000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-92387-6_24"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031923869","9783031923876"],"references-count":81,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-92387-6_24","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"12 May 2025","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"}}]}}