{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T21:02:17Z","timestamp":1784408537009,"version":"3.55.0"},"publisher-location":"Singapore","reference-count":31,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819234028","type":"print"},{"value":"9789819234035","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,7,19]],"date-time":"2026-07-19T00:00:00Z","timestamp":1784419200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,7,19]],"date-time":"2026-07-19T00:00:00Z","timestamp":1784419200000},"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":[[2027]]},"DOI":"10.1007\/978-981-92-3403-5_32","type":"book-chapter","created":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T20:08:49Z","timestamp":1784405329000},"page":"405-416","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["ZeroForge: Zero-Shot 6D Pose Estimation via Generative 3D Reconstruction and Vision-Language Models"],"prefix":"10.1007","author":[{"given":"Binglin","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bo","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Boping","family":"Ran","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chengkun","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,19]]},"reference":[{"key":"32_CR1","unstructured":"Bai, J., et al.: Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond. https:\/\/arxiv.org\/abs\/2308.12966 (2023)."},{"key":"32_CR2","doi-asserted-by":"crossref","unstructured":"Cai, D., Heikkil\u00e4, J., Rahtu, E.: GS-Pose: Cascaded Framework for Generalizable Segmentation-based 6D Object Pose Estimation. In: ECCV (2024).","DOI":"10.1109\/3DV66043.2025.00097"},{"key":"32_CR3","unstructured":"Deng, J., et al.: Pos3R: One-Shot 6D Pose Estimation via 3D Reconstruction Priors. In: CVPR (2025)."},{"key":"32_CR4","volume-title":"Deep learning-based object pose estimation: a comprehensive survey","author":"J Fan","year":"2025","unstructured":"Fan, J., et al.: Deep learning-based object pose estimation: a comprehensive survey. Int. J. Comput, Vis (2025)"},{"issue":"5","key":"32_CR5","doi-asserted-by":"publisher","first-page":"701","DOI":"10.1177\/02783649241281508","volume":"44","author":"R Firoozi","year":"2025","unstructured":"Firoozi, R., et al.: foundation models in robotics: applications, challenges, and the future. Int. J. Robot. Res. 44(5), 701\u2013739 (2025)","journal-title":"Int. J. Robot. Res."},{"key":"32_CR6","doi-asserted-by":"crossref","unstructured":"Hoda, T., et al.: BOP Challenge 2023 on Detection, Segmentation and Pose Esti- mation of Seen and Unseen Rigid Objects. In: CVPRW (2024).","DOI":"10.1109\/CVPRW63382.2024.00570"},{"key":"32_CR7","unstructured":"Hoda, T., et al.: BOP Challenge 2024 on Model-Based and Model-Free 6D Object Pose Estimation. https:\/\/arxiv.org\/abs\/2504.02812 (2025)."},{"key":"32_CR8","unstructured":"Hsieh, J., Tu, K.-H., Hung, K.-H., & Ke, T.-W.: DexMan: Dexterous Manipulation with Affordance-Guided Neural Networks. In: CVPR (2024)."},{"issue":"3","key":"32_CR9","doi-asserted-by":"publisher","first-page":"535","DOI":"10.1109\/TBDATA.2019.2921572","volume":"7","author":"J Johnson","year":"2019","unstructured":"Johnson, J., Douze, M., J\u00e9gou, H.: Billion-scale similarity search with GPUs. IEEE Trans Big Data. 7(3), 535\u2013547 (2019)","journal-title":"IEEE Trans Big Data"},{"key":"32_CR10","doi-asserted-by":"crossref","unstructured":"Lee, T., Wen, B., Kang, M., Kang, G., Kweon, I. S., & Yoon, K.-J.: Any6D: Model-Free 6D Pose Estimation of Novel Objects. In: CVPR (2025).","DOI":"10.1109\/CVPR52734.2025.01086"},{"key":"32_CR11","unstructured":"Li, K., Li, P., Liu, T., Li, Y., Huang, S.: ManiTrans: Dexterous Manipulation via Transfer of Human Hand Knowledge. In: ICRA (2025)."},{"key":"32_CR12","doi-asserted-by":"crossref","unstructured":"Lin, J., Liu, M., Lu, Z., Jia, K.: SAM-6D: Segment Anything Model Meets Zero- Shot 6D Object Pose Estimation. In: CVPR (2024).","DOI":"10.1109\/CVPR52733.2024.02636"},{"key":"32_CR13","doi-asserted-by":"crossref","unstructured":"Liu, S., et al.: Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection. In: ECCV (2024).","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"32_CR14","doi-asserted-by":"crossref","unstructured":"Liu, R., et al.: Zero-1-to-3: Zero-Shot One Image to 3D Object. In: ICCV (2023).","DOI":"10.1109\/ICCV51070.2023.00853"},{"key":"32_CR15","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual Instruction Tuning. In: NeurIPS (2023).","DOI":"10.52202\/075280-1516"},{"key":"32_CR16","doi-asserted-by":"crossref","unstructured":"Liu, M., Li, S., Chhatkuli, A., Truong, P., Van Gool, L., & Tombari, F.: One2Any: Single Reference 6D Object Pose Estimation. In: CVPR (2025).","DOI":"10.1109\/CVPR52734.2025.00605"},{"key":"32_CR17","doi-asserted-by":"crossref","unstructured":"Nguyen, V.N., Groueix, T., Salzmann, M., Lepetit, V.: GigaPose: Fast and Robust Novel Object Pose Estimation via One Correspondence. In: CVPR (2024).","DOI":"10.1109\/CVPR52733.2024.00945"},{"key":"32_CR18","unstructured":"OpenAI: GPT-4V(ision) System Card. OpenAI Technical Report (2023)."},{"issue":"2","key":"32_CR19","doi-asserted-by":"publisher","first-page":"155","DOI":"10.1093\/comjnl\/7.2.155","volume":"7","author":"MJD Powell","year":"1964","unstructured":"Powell, M.J.D.: An efficient method for finding the minimum of a function of several variables without calculating derivatives. Comput. J. 7(2), 155\u2013162 (1964)","journal-title":"Comput. J."},{"key":"32_CR20","unstructured":"Ravi, N., et al.: SAM 2: Segment Anything in Images and Videos. https:\/\/arxiv.org\/abs\/2408.00714 (2024)."},{"key":"32_CR21","doi-asserted-by":"crossref","unstructured":"Wang, C.-Y., Yeh, I.-H., Liao, H.-Y.M.: YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information. In: ECCV (2024).","DOI":"10.1007\/978-3-031-72751-1_1"},{"key":"32_CR22","doi-asserted-by":"crossref","unstructured":"Wen, B., Yang, W., Kautz, J., Birchfield, S.: FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects. In: CVPR, pp. 17868\u201317879 (2024).","DOI":"10.1109\/CVPR52733.2024.01692"},{"key":"32_CR23","doi-asserted-by":"crossref","unstructured":"Xiang, J., et al.: Structured 3D Latents for Scalable and Versatile 3D Generation. https:\/\/arxiv.org\/abs\/2412.01506 (2024).","DOI":"10.1109\/CVPR52734.2025.02000"},{"key":"32_CR24","unstructured":"Xiang, J., et al.: TRELLIS.2: Native and Compact Structured Latents for 3D Generation. https:\/\/arxiv.org\/abs\/2512.14692 (2025)."},{"key":"32_CR25","unstructured":"Xu, J., et al.: InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-View Large Reconstruction Models. https:\/\/arxiv.org\/abs\/2404.07191 (2024)."},{"key":"32_CR26","doi-asserted-by":"crossref","unstructured":"Yang, L., et al.: Depth Anything V2. In: NeurIPS (2024).","DOI":"10.52202\/079017-0688"},{"issue":"2","key":"32_CR27","doi-asserted-by":"publisher","first-page":"239","DOI":"10.1109\/34.121791","volume":"14","author":"PJ Besl","year":"1992","unstructured":"Besl, P.J., McKay, N.D.: A method for registration of 3-D shapes. IEEE Trans. Pattern Anal. Mach. Intell. 14(2), 239\u2013256 (1992)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"32_CR28","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. In: ICCV, pp. 2961\u20132969 (2017).","DOI":"10.1109\/ICCV.2017.322"},{"issue":"2","key":"32_CR29","doi-asserted-by":"publisher","first-page":"179","DOI":"10.1109\/TIT.1962.1057692","volume":"8","author":"MK Hu","year":"1962","unstructured":"Hu, M.K.: Visual pattern recognition by moment invariants. IRE Trans. Inf. The- ory. 8(2), 179\u2013187 (1962)","journal-title":"IRE Trans. Inf. The- ory"},{"key":"32_CR30","unstructured":"Kirillov, A., et al.: Segment Anything. In: ICCV, pp. 4015\u20134026 (2023)."},{"key":"32_CR31","unstructured":"Oquab, M., et al.: DINOv2: Learning Robust Visual Features without Supervision. Trans. Mach. Learn Res. (2024)."}],"container-title":["Lecture Notes in Computer Science","Advanced Intelligent Computing Technology and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-92-3403-5_32","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T20:08:52Z","timestamp":1784405332000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-92-3403-5_32"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,19]]},"ISBN":["9789819234028","9789819234035"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-981-92-3403-5_32","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,19]]},"assertion":[{"value":"19 July 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Toronto","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Canada","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":"22 July 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 July 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icic2026a","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/2026\/index.htm","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}