{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,29]],"date-time":"2026-01-29T21:22:59Z","timestamp":1769721779789,"version":"3.49.0"},"publisher-location":"Cham","reference-count":63,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031728969","type":"print"},{"value":"9783031728976","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"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\/978-3-031-72897-6_15","type":"book-chapter","created":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T21:36:21Z","timestamp":1733088981000},"page":"259-276","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["DreamReward: Text-to-3D Generation with\u00a0Human Preference"],"prefix":"10.1007","author":[{"given":"JunLiang","family":"Ye","sequence":"first","affiliation":[]},{"given":"Fangfu","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Qixiu","family":"Li","sequence":"additional","affiliation":[]},{"given":"Zhengyi","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Yikai","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Xinzhou","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Yueqi","family":"Duan","sequence":"additional","affiliation":[]},{"given":"Jun","family":"Zhu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,12,2]]},"reference":[{"key":"15_CR1","unstructured":"Achiam, J., et\u00a0al.: Gpt-4 technical report. arXiv preprint arXiv:2303.08774 (2023)"},{"key":"15_CR2","unstructured":"Black, K., Janner, M., Du, Y., Kostrikov, I., Levine, S.: Training diffusion models with reinforcement learning. arXiv preprint arXiv:2305.13301 (2023)"},{"key":"15_CR3","unstructured":"Chang, A.X., et al.: Shapenet: an information-rich 3d model repository (2015)"},{"key":"15_CR4","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 (ICCV), pp. 22246\u201322256 (2023)","DOI":"10.1109\/ICCV51070.2023.02033"},{"key":"15_CR5","doi-asserted-by":"crossref","unstructured":"Chen, Y., et al.: Gaussianeditor: swift and controllable 3d editing with gaussian splatting. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). pp. 21476\u201321485 (2024)","DOI":"10.1109\/CVPR52733.2024.02029"},{"key":"15_CR6","doi-asserted-by":"crossref","unstructured":"Deitke, M., et al.: Objaverse: a universe of annotated 3d objects (2022)","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"15_CR7","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":"15_CR8","doi-asserted-by":"crossref","unstructured":"Ding, L., et al.: Text-to-3d generation with bidirectional diffusion using both 2d and 3d priors. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5115\u20135124 (2024)","DOI":"10.1109\/CVPR52733.2024.00489"},{"key":"15_CR9","unstructured":"Fan, Y., et al.: Reinforcement learning for fine-tuning text-to-image diffusion models. Adv. Neural Inf. Process. Syst. 36 (2024)"},{"key":"15_CR10","unstructured":"Guo, Y.C., et al.: Threestudio: a unified framework for 3d content generation (2023). https:\/\/github.com\/threestudio-project\/threestudio"},{"key":"15_CR11","unstructured":"Gupta, A., Xiong, W., Nie, Y., Jones, I., O\u011fuz, B.: 3dgen: triplane latent diffusion for textured mesh generation (2023)"},{"key":"15_CR12","unstructured":"He, Y., et al.: T$$^3$$bench: benchmarking current progress in text-to-3d generation (2023)"},{"key":"15_CR13","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":"15_CR14","doi-asserted-by":"crossref","unstructured":"H\u00f6llein, L., Cao, A., Owens, A., Johnson, J., Nie\u00dfner, M.: Text2room: extracting textured 3d meshes from 2d text-to-image models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7909\u20137920 (2023)","DOI":"10.1109\/ICCV51070.2023.00727"},{"key":"15_CR15","doi-asserted-by":"crossref","unstructured":"H\u00f6llein, L., et\u00a0al.: Viewdiff: 3d-consistent image generation with text-to-image models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5043\u20135052 (2024)","DOI":"10.1109\/CVPR52733.2024.00482"},{"key":"15_CR16","unstructured":"Hong, Y., et al.: Lrm: large reconstruction model for single image to 3d (2023)"},{"key":"15_CR17","doi-asserted-by":"crossref","unstructured":"Jain, A., Mildenhall, B., Barron, J.T., Abbeel, P., Poole, B.: Zero-shot text-guided object generation with dream fields. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 867\u2013876 (2022)","DOI":"10.1109\/CVPR52688.2022.00094"},{"key":"15_CR18","unstructured":"Jun, H., Nichol, A.: Shap-e: generating conditional 3d implicit functions (2023)"},{"key":"15_CR19","doi-asserted-by":"crossref","unstructured":"Kerbl, B., Kopanas, G., Leimk\u00fchler, T., Drettakis, G.: 3d gaussian splatting for real-time radiance field rendering. ACM Trans. Graph. 42(4) (2023). https:\/\/repo-sam.inria.fr\/fungraph\/3d-gaussian-splatting\/","DOI":"10.1145\/3592433"},{"key":"15_CR20","unstructured":"Li, J., Li, D., Savarese, S., Hoi, S.: Blip-2: bootstrapping language-image pre-training with frozen image encoders and large language models. In: International Conference on Machine Learning, pp. 19730\u201319742. PMLR (2023)"},{"key":"15_CR21","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":"15_CR22","unstructured":"Li, W., Chen, R., Chen, X., Tan, P.: Sweetdreamer: aligning geometric priors in 2d diffusion for consistent text-to-3d. arxiv:2310.02596 (2023)"},{"key":"15_CR23","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":"15_CR24","doi-asserted-by":"crossref","unstructured":"Lin, C.H., et al.: Magic3d: high-resolution text-to-3d content creation. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2023)","DOI":"10.1109\/CVPR52729.2023.00037"},{"key":"15_CR25","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 (CVPR), pp. 20763\u201320774 (2024)","DOI":"10.1109\/CVPR52733.2024.01962"},{"key":"15_CR26","unstructured":"Liu, F., et\u00a0al.: Learning to summarize from human feedback. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (2020)"},{"key":"15_CR27","doi-asserted-by":"crossref","unstructured":"Liu, M., et al.: One-2-3-45++: fast single image to 3d objects with consistent multi-view generation and 3d diffusion. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10072\u201310083 (2024)","DOI":"10.1109\/CVPR52733.2024.00960"},{"key":"15_CR28","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":"15_CR29","unstructured":"Liu, Y., et al.: Syncdreamer: generating multiview-consistent images from a single-view image. arXiv preprint arXiv:2309.03453 (2023)"},{"key":"15_CR30","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization (2019)"},{"key":"15_CR31","unstructured":"Luo, T., Rockwell, C., Lee, H., Johnson, J.: Scalable 3d captioning with pretrained models. Adv. Neural Inf. Process. Syst. 36 (2024)"},{"key":"15_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":"15_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":"15_CR34","unstructured":"Nichol, A., et al.: Glide: towards photorealistic image generation and editing with text-guided diffusion models (2022)"},{"key":"15_CR35","unstructured":"Nichol, A., Jun, H., Dhariwal, P., Mishkin, P., Chen, M.: Point-e: a system for generating 3d point clouds from complex prompts (2022)"},{"key":"15_CR36","unstructured":"Achiam, J., Adler, S., Agarwal, S., et\u00a0al.: OpenAI: Gpt-4 technical report (2023)"},{"key":"15_CR37","first-page":"27730","volume":"35","author":"L Ouyang","year":"2022","unstructured":"Ouyang, L., et al.: Training language models to follow instructions with human feedback. Adv. Neural. Inf. Process. Syst. 35, 27730\u201327744 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"15_CR38","unstructured":"Poole, B., Jain, A., Barron, J.T., Mildenhall, B.: Dreamfusion: text-to-3d using 2d diffusion. arXiv preprint arXiv:2209.14988 (2022)"},{"key":"15_CR39","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":"15_CR40","unstructured":"Rafailov, R., Sharma, A., Mitchell, E., Manning, C.D., Ermon, S., Finn, C.: Direct preference optimization: Your language model is secretly a reward model. Adv. Neural Inf. Process. Syst. 36 (2024)"},{"key":"15_CR41","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., Chen, M.: Hierarchical text-conditional image generation with clip latents, 1(2), 3 (2022). arXiv preprint arXiv:2204.06125"},{"key":"15_CR42","unstructured":"Roberts, A., et al.: Exploring the limits of transfer learning with a unified text-to-text transformer. Technical report, Google (2019)"},{"key":"15_CR43","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":"15_CR44","unstructured":"Shi, R., et al.: Zero123++: a single image to consistent multi-view diffusion base model. arXiv preprint arXiv:2310.15110 (2023)"},{"key":"15_CR45","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":"15_CR46","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":"15_CR47","unstructured":"Tang, J., Ren, J., Zhou, H., Liu, Z., Zeng, G.: Dreamgaussian: generative gaussian splatting for efficient 3d content creation. arXiv preprint arXiv:2309.16653 (2023)"},{"key":"15_CR48","unstructured":"Team, G., Anil, R., Borgeaud, S., et\u00a0al.: Gemini: a family of highly capable multimodal models (2023)"},{"key":"15_CR49","doi-asserted-by":"crossref","unstructured":"Wada, Y., Kaneda, K., Saito, D., Sugiura, K.: Polos: Multimodal metric learning from human feedback for image captioning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13559\u201313568 (2024)","DOI":"10.1109\/CVPR52733.2024.01287"},{"key":"15_CR50","doi-asserted-by":"crossref","unstructured":"Wallace, B., et al.: Diffusion model alignment using direct preference optimization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8228\u20138238 (2024)","DOI":"10.1109\/CVPR52733.2024.00786"},{"key":"15_CR51","doi-asserted-by":"crossref","unstructured":"Wang, H., Du, X., Li, J., Yeh, R.A., Shakhnarovich, G.: Score jacobian chaining: lifting pretrained 2d diffusion models for 3d generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12619\u201312629 (2023)","DOI":"10.1109\/CVPR52729.2023.01214"},{"key":"15_CR52","unstructured":"Wang, Z., et al.: Prolificdreamer: high-fidelity and diverse text-to-3d generation with variational score distillation. Adv. Neural Inf. Process. Syst. 36 (2024)"},{"key":"15_CR53","doi-asserted-by":"crossref","unstructured":"Wang, Z., et al.: Crm: single image to 3d textured mesh with convolutional reconstruction model. arXiv preprint arXiv:2403.05034 (2024)","DOI":"10.1007\/978-3-031-72751-1_4"},{"key":"15_CR54","doi-asserted-by":"crossref","unstructured":"Wei, M., Zhou, J., Sun, J., Zhang, X.: Adversarial score distillation: when score distillation meets gan. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8131\u20138141 (2024)","DOI":"10.1109\/CVPR52733.2024.00777"},{"key":"15_CR55","doi-asserted-by":"crossref","unstructured":"Wu, T., et al.: Gpt-4v (ision) is a human-aligned evaluator for text-to-3d generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 22227\u201322238 (2024)","DOI":"10.1109\/CVPR52733.2024.02098"},{"key":"15_CR56","unstructured":"Xu, J., et al.: Imagereward: learning and evaluating human preferences for text-to-image generation. Adv. Neural Inf. Process. Syst. 36 (2024)"},{"key":"15_CR57","doi-asserted-by":"crossref","unstructured":"Yang, K., et al.: Using human feedback to fine-tune diffusion models without any reward model. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8941\u20138951 (2024)","DOI":"10.1109\/CVPR52733.2024.00854"},{"key":"15_CR58","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":"15_CR59","unstructured":"Zhao, R., Wang, Z., Wang, Y., Zhou, Z., Zhu, J.: Flexidreamer: single image-to-3d generation with flexicubes. arXiv preprint arXiv:2404.00987 (2024)"},{"key":"15_CR60","unstructured":"Zhu, J., Zhuang, P.: Hifa: high-fidelity text-to-3d generation with advanced diffusion guidance (2023)"},{"key":"15_CR61","unstructured":"Zhu, Z., et al.: Diffusion models for reinforcement learning: a survey (2024)"},{"key":"15_CR62","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"},{"key":"15_CR63","unstructured":"Ziegler, D.M., et al.: Fine-tuning language models from human preferences (2020)"}],"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\/978-3-031-72897-6_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T23:19:15Z","timestamp":1733095155000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72897-6_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,2]]},"ISBN":["9783031728969","9783031728976"],"references-count":63,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72897-6_15","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,2]]},"assertion":[{"value":"2 December 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"}}]}}