{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,25]],"date-time":"2026-09-25T08:34:44Z","timestamp":1790325284044,"version":"4.1.0"},"publisher-location":"Cham","reference-count":55,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031726484","type":"print"},{"value":"9783031726491","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T00:00:00Z","timestamp":1727654400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T00:00:00Z","timestamp":1727654400000},"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\/978-3-031-72649-1_25","type":"book-chapter","created":{"date-parts":[[2024,9,29]],"date-time":"2024-09-29T07:01:50Z","timestamp":1727593310000},"page":"438-455","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["TPA3D: Triplane Attention for\u00a0Fast Text-to-3D Generation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-7557-7637","authenticated-orcid":false,"given":"Bin-Shih","family":"Wu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8787-4234","authenticated-orcid":false,"given":"Hong-En","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3149-9620","authenticated-orcid":false,"given":"Sheng-Yu","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2333-157X","authenticated-orcid":false,"given":"Yu-Chiang Frank","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,9,30]]},"reference":[{"key":"25_CR1","unstructured":"Achlioptas, P., Diamanti, O., Mitliagkas, I., Guibas, L.: Learning representations and generative models for 3D point clouds. In: International Conference on Machine Learning, pp. 40\u201349. PMLR (2018)"},{"key":"25_CR2","unstructured":"Arjovsky, M., Chintala, S., Bottou, L.: Wasserstein generative adversarial networks. In: International Conference on Machine Learning, pp. 214\u2013223. PMLR (2017)"},{"key":"25_CR3","unstructured":"Cao, Z., Hong, F., Wu, T., Pan, L., Liu, Z.: Large-vocabulary 3D diffusion model with transformer. arXiv preprint arXiv:2309.07920 (2023)"},{"key":"25_CR4","doi-asserted-by":"crossref","unstructured":"Chan, E.R., et\u00a0al.: Efficient geometry-aware 3D generative adversarial networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16123\u201316133 (2022)","DOI":"10.1109\/CVPR52688.2022.01565"},{"key":"25_CR5","unstructured":"Chang, A.X., et\u00a0al.: Shapenet: an information-rich 3D model repository. arXiv preprint arXiv:1512.03012 (2015)"},{"issue":"4","key":"25_CR6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3592116","volume":"42","author":"H Chefer","year":"2023","unstructured":"Chefer, H., Alaluf, Y., Vinker, Y., Wolf, L., Cohen-Or, D.: Attend-and-excite: attention-based semantic guidance for text-to-image diffusion models. ACM Trans. Graphics (TOG) 42(4), 1\u201310 (2023)","journal-title":"ACM Trans. Graphics (TOG)"},{"key":"25_CR7","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"100","DOI":"10.1007\/978-3-030-20893-6_7","volume-title":"Computer Vision \u2013 ACCV 2018","author":"K Chen","year":"2019","unstructured":"Chen, K., Choy, C.B., Savva, M., Chang, A.X., Funkhouser, T., Savarese, S.: Text2Shape: generating shapes from natural language by learning joint embeddings. In: Jawahar, C.V., Li, H., Mori, G., Schindler, K. (eds.) ACCV 2018. LNCS, vol. 11363, pp. 100\u2013116. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-20893-6_7"},{"key":"25_CR8","unstructured":"Chen, M., et al.: Generative pretraining from pixels. In: International Conference on Machine Learning, pp. 1691\u20131703. PMLR (2020)"},{"key":"25_CR9","doi-asserted-by":"crossref","unstructured":"Chen, Z., Zhang, H.: Learning implicit fields for generative shape modeling. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5939\u20135948 (2019)","DOI":"10.1109\/CVPR.2019.00609"},{"key":"25_CR10","doi-asserted-by":"crossref","unstructured":"Cheng, Y.C., Lee, H.Y., Tulyakov, S., Schwing, A.G., Gui, L.Y.: SDFusion: multimodal 3D shape completion, reconstruction, and generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4456\u20134465 (2023)","DOI":"10.1109\/CVPR52729.2023.00433"},{"key":"25_CR11","unstructured":"Dai, W., et al.: Instructblip: towards general-purpose vision-language models with instruction tuning (2023)"},{"key":"25_CR12","first-page":"19822","volume":"34","author":"M Ding","year":"2021","unstructured":"Ding, M., et al.: CogView: mastering text-to-image generation via transformers. Adv. Neural. Inf. Process. Syst. 34, 19822\u201319835 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"25_CR13","unstructured":"Feng, W., et al.: Training-free structured diffusion guidance for compositional text-to-image synthesis. arXiv preprint arXiv:2212.05032 (2022)"},{"key":"25_CR14","first-page":"8882","volume":"35","author":"R Fu","year":"2022","unstructured":"Fu, R., Zhan, X., Chen, Y., Ritchie, D., Sridhar, S.: Shapecrafter: a recursive text-conditioned 3d shape generation model. Adv. Neural. Inf. Process. Syst. 35, 8882\u20138895 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"25_CR15","first-page":"31841","volume":"35","author":"J Gao","year":"2022","unstructured":"Gao, J., et al.: Get3D: a generative model of high quality 3d textured shapes learned from images. Adv. Neural. Inf. Process. Syst. 35, 31841\u201331854 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"25_CR16","unstructured":"Ha, H., Agrawal, S., Song, S.: Fit2form: 3D generative model for robot gripper form design. In: Conference on Robot Learning, pp. 176\u2013187. PMLR (2021)"},{"key":"25_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":"25_CR18","unstructured":"Huang, T., et al.: Textfield3d: towards enhancing open-vocabulary 3D generation with noisy text fields. arXiv preprint arXiv:2309.17175 (2023)"},{"key":"25_CR19","unstructured":"Jia, C., et al.: Scaling up visual and vision-language representation learning with noisy text supervision. In: International Conference on Machine Learning, pp. 4904\u20134916. PMLR (2021)"},{"key":"25_CR20","doi-asserted-by":"crossref","unstructured":"Kang, M., et al.: Scaling up GANs for text-to-image synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10124\u201310134 (2023)","DOI":"10.1109\/CVPR52729.2023.00976"},{"key":"25_CR21","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":"25_CR22","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":"25_CR23","doi-asserted-by":"crossref","unstructured":"Katara, P., Xian, Z., Fragkiadaki, K.: Gen2sim: scaling up robot learning in simulation with generative models. arXiv preprint arXiv:2310.18308 (2023)","DOI":"10.1109\/ICRA57147.2024.10610566"},{"issue":"6","key":"25_CR24","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3414685.3417861","volume":"39","author":"S Laine","year":"2020","unstructured":"Laine, S., Hellsten, J., Karras, T., Seol, Y., Lehtinen, J., Aila, T.: Modular primitives for high-performance differentiable rendering. ACM Trans. Graphics (TOG) 39(6), 1\u201314 (2020)","journal-title":"ACM Trans. Graphics (TOG)"},{"key":"25_CR25","unstructured":"Li, J., Li, D., Savarese, S., Hoi, S.: Blip-2: bootstrapping language-image pre-training with frozen image encoders and large language models. arXiv preprint arXiv:2301.12597 (2023)"},{"key":"25_CR26","unstructured":"Li, J., Li, D., Xiong, C., Hoi, S.: Blip: bootstrapping language-image pre-training for unified vision-language understanding and generation. In: International Conference on Machine Learning, pp. 12888\u201312900. PMLR (2022)"},{"key":"25_CR27","unstructured":"Li, K., Malik, J.: Implicit maximum likelihood estimation. arXiv preprint arXiv:1809.09087 (2018)"},{"key":"25_CR28","doi-asserted-by":"crossref","unstructured":"Li, M., Duan, Y., Zhou, J., Lu, J.: Diffusion-SDF: text-to-shape via voxelized diffusion. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12642\u201312651 (2023)","DOI":"10.1109\/CVPR52729.2023.01216"},{"key":"25_CR29","doi-asserted-by":"crossref","unstructured":"Lin, C.H., et al.: Magic3D: high-resolution text-to-3D content creation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 300\u2013309 (2023)","DOI":"10.1109\/CVPR52729.2023.00037"},{"key":"25_CR30","doi-asserted-by":"crossref","unstructured":"Liu, Z., Wang, Y., Qi, X., Fu, C.W.: Towards implicit text-guided 3D shape generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 17896\u201317906 (2022)","DOI":"10.1109\/CVPR52688.2022.01737"},{"key":"25_CR31","doi-asserted-by":"crossref","unstructured":"Mescheder, L., Oechsle, M., Niemeyer, M., Nowozin, S., Geiger, A.: Occupancy networks: learning 3D reconstruction in function space. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4460\u20134470 (2019)","DOI":"10.1109\/CVPR.2019.00459"},{"key":"25_CR32","doi-asserted-by":"crossref","unstructured":"Metzer, G., Richardson, E., Patashnik, O., Giryes, R., Cohen-Or, D.: Latent-nerf for shape-guided generation of 3D shapes and textures. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12663\u201312673 (2023)","DOI":"10.1109\/CVPR52729.2023.01218"},{"issue":"1","key":"25_CR33","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":"25_CR34","doi-asserted-by":"crossref","unstructured":"Mittal, P., Cheng, Y.C., Singh, M., Tulsiani, S.: AutoSDF: shape priors for 3d completion, reconstruction and generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 306\u2013315 (2022)","DOI":"10.1109\/CVPR52688.2022.00040"},{"key":"25_CR35","unstructured":"Park, D.H., Azadi, S., Liu, X., Darrell, T., Rohrbach, A.: Benchmark for compositional text-to-image synthesis. In: Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 1) (2021)"},{"key":"25_CR36","doi-asserted-by":"crossref","unstructured":"Pavllo, D., Kohler, J., Hofmann, T., Lucchi, A.: Learning generative models of textured 3D meshes from real-world images. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 13879\u201313889 (2021)","DOI":"10.1109\/ICCV48922.2021.01362"},{"key":"25_CR37","unstructured":"Poole, B., Jain, A., Barron, J.T., Mildenhall, B.: Dreamfusion: text-to-3D using 2D diffusion. arXiv preprint arXiv:2209.14988 (2022)"},{"key":"25_CR38","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"25_CR39","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., Chen, M.: Hierarchical text-conditional image generation with clip Latents. arXiv preprint arXiv:2204.061251(2), 3 (2022)"},{"key":"25_CR40","unstructured":"Ramesh, A., et al.: Zero-shot text-to-image generation. In: International Conference on Machine Learning, pp. 8821\u20138831. PMLR (2021)"},{"key":"25_CR41","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":"25_CR42","first-page":"36479","volume":"35","author":"C Saharia","year":"2022","unstructured":"Saharia, C., et al.: Photorealistic text-to-image diffusion models with deep language understanding. Adv. Neural. Inf. Process. Syst. 35, 36479\u201336494 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"25_CR43","doi-asserted-by":"crossref","unstructured":"Sanghi, A., et al.: Clip-forge: Towards zero-shot text-to-shape generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18603\u201318613 (2022)","DOI":"10.1109\/CVPR52688.2022.01805"},{"key":"25_CR44","doi-asserted-by":"crossref","unstructured":"Sanghi, A., et al.: Clip-sculptor: zero-shot generation of high-fidelity and diverse shapes from natural language. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18339\u201318348 (2023)","DOI":"10.1109\/CVPR52729.2023.01759"},{"key":"25_CR45","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":"25_CR46","doi-asserted-by":"crossref","unstructured":"Sharma, P., Ding, N., Goodman, S., Soricut, R.: Conceptual captions: a cleaned, hypernymed, image alt-text dataset for automatic image captioning. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics, pp. 2556\u20132565 (2018)","DOI":"10.18653\/v1\/P18-1238"},{"key":"25_CR47","first-page":"6087","volume":"34","author":"T Shen","year":"2021","unstructured":"Shen, T., Gao, J., Yin, K., Liu, M.Y., Fidler, S.: Deep marching tetrahedra: a hybrid representation for high-resolution 3D shape synthesis. Adv. Neural. Inf. Process. Syst. 34, 6087\u20136101 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"25_CR48","doi-asserted-by":"crossref","unstructured":"Tao, M., Bao, B.K., Tang, H., Xu, C.: Galip: generative adversarial clips for text-to-image synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14214\u201314223 (2023)","DOI":"10.1109\/CVPR52729.2023.01366"},{"key":"25_CR49","unstructured":"Van Den\u00a0Oord, A., Vinyals, O., et\u00a0al.: Neural discrete representation learning. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"25_CR50","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"25_CR51","doi-asserted-by":"crossref","unstructured":"Wang, C., Chai, M., He, M., Chen, D., Liao, J.: Clip-nerf: text-and-image driven manipulation of neural radiance fields. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3835\u20133844 (2022)","DOI":"10.1109\/CVPR52688.2022.00381"},{"key":"25_CR52","doi-asserted-by":"crossref","unstructured":"Wei, J., Wang, H., Feng, J., Lin, G., Yap, K.H.: Taps3D: text-guided 3D textured shape generation from pseudo supervision. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16805\u201316815 (2023)","DOI":"10.1109\/CVPR52729.2023.01612"},{"key":"25_CR53","doi-asserted-by":"crossref","unstructured":"Wu, T., et\u00a0al.: Omniobject3D: large-vocabulary 3D object dataset for realistic perception, reconstruction and generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 803\u2013814 (2023)","DOI":"10.1109\/CVPR52729.2023.00084"},{"key":"25_CR54","doi-asserted-by":"crossref","unstructured":"Xu, J., et al.: Dream3D: zero-shot text-to-3D synthesis using 3D shape prior and text-to-image diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 20908\u201320918 (2023)","DOI":"10.1109\/CVPR52729.2023.02003"},{"key":"25_CR55","doi-asserted-by":"crossref","unstructured":"Yang, G., Huang, X., Hao, Z., Liu, M.Y., Belongie, S., Hariharan, B.: Pointflow: 3D point cloud generation with continuous normalizing flows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4541\u20134550 (2019)","DOI":"10.1109\/ICCV.2019.00464"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72649-1_25","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,29]],"date-time":"2024-09-29T07:13:23Z","timestamp":1727594003000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72649-1_25"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,30]]},"ISBN":["9783031726484","9783031726491"],"references-count":55,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72649-1_25","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,9,30]]},"assertion":[{"value":"30 September 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}