{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T07:02:28Z","timestamp":1790233348868,"version":"4.1.0"},"publisher-location":"Cham","reference-count":39,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032374608","type":"print"},{"value":"9783032374615","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\/978-3-032-37461-5_11","type":"book-chapter","created":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T06:34:48Z","timestamp":1790231688000},"page":"195-212","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Ground3D-LMM: Fine-Grained 3D Point Grounding and\u00a0Spatial Reasoning with\u00a0LMM"],"prefix":"10.1007","author":[{"given":"Amol","family":"Harsh","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zongyan","family":"Han","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jean","family":"Lahoud","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ye","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rao Muhammad","family":"Anwer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hisham","family":"Cholakkal","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Salman","family":"Khan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fahad Shahbaz","family":"Khan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,25]]},"reference":[{"key":"11_CR1","doi-asserted-by":"crossref","unstructured":"Achlioptas, P., Abdelreheem, A., Xia, F., Elhoseiny, M., Guibas, L.: Referit3D: neural listeners for fine-grained 3D object identification in real-world scenes. In: European Conference on Computer Vision, pp. 422\u2013440. Springer (2020)","DOI":"10.1007\/978-3-030-58452-8_25"},{"key":"11_CR2","doi-asserted-by":"crossref","unstructured":"Ahmed, M., Fei, J., Ding, J., Bakr, E.M., Elhoseiny, M.: Kestrel: 3D multimodal llm for part-aware grounded description. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 8973\u20138983 (2025)","DOI":"10.1109\/ICCV51701.2025.00839"},{"key":"11_CR3","doi-asserted-by":"crossref","unstructured":"Azuma, D., Miyanishi, T., Kurita, S., Kawanabe, M.: Scanqa: 3D question answering for spatial scene understanding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19129\u201319139 (2022)","DOI":"10.1109\/CVPR52688.2022.01854"},{"key":"11_CR4","unstructured":"Bai, S., Cai, Y., Chen, R., Chen, K., Chen, X., Cheng, Z., Deng, L., Ding, W., Gao, C., Ge, C., et\u00a0al.: Qwen3-vl Technical Report (2025). arXiv preprint arXiv:2511.21631"},{"key":"11_CR5","unstructured":"Boudjoghra, M.E.A., Dai, A., Lahoud, J., Cholakkal, H., Anwer, R.M., Khan, S., Khan, F.S.: OPEN-YOLO 3D: towards fast and accurate open-vocabulary 3D instance segmentation. In: 13th International Conference on Learning Representations, ICLR 2025, pp. 26618\u201326631. International Conference on Learning Representations, ICLR (2025)"},{"key":"11_CR6","doi-asserted-by":"crossref","unstructured":"Chen, B., Xu, Z., Kirmani, S., Ichter, B., Sadigh, D., Guibas, L., Xia, F.: Spatialvlm: endowing vision-language models with spatial reasoning capabilities. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14455\u201314465 (2024)","DOI":"10.1109\/CVPR52733.2024.01370"},{"key":"11_CR7","doi-asserted-by":"crossref","unstructured":"Chen, D.Z., Chang, A.X., Nie\u00dfner, M.: Scanrefer: 3D object localization in RGB-D scans using natural language. In: ECCV, pp. 202\u2013221. Springer (2020)","DOI":"10.1007\/978-3-030-58565-5_13"},{"key":"11_CR8","doi-asserted-by":"crossref","unstructured":"Chen, P., Lou, Y., Cao, S., Guo, J., Fan, L., Wu, Y., Yang, L., Ma, L., Ye, J.: SD-VLM: Spatial Measuring and Understanding with Depth-Encoded Vision-Language Models (2025). arXiv:2509.17664 arXiv preprint","DOI":"10.52202\/085713-1140"},{"key":"11_CR9","doi-asserted-by":"publisher","first-page":"135062","DOI":"10.52202\/079017-4293","volume":"37","author":"AC Cheng","year":"2024","unstructured":"Cheng, A.C., Yin, H., Fu, Y., Guo, Q., Yang, R., Kautz, J., Wang, X., Liu, S.: SpatialRGPT: grounded spatial reasoning in vision-language models. Adv. Neural. Inf. Process. Syst. 37, 135062\u2013135093 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"11_CR10","doi-asserted-by":"crossref","unstructured":"Choy, C., Gwak, J., Savarese, S.: 4D spatio-temporal convnets: Minkowski convolutional neural networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3075\u20133084 (2019)","DOI":"10.1109\/CVPR.2019.00319"},{"key":"11_CR11","unstructured":"Contributors, S.: Spconv: Spatially Sparse Convolution Library (2022). https:\/\/github.com\/traveller59\/spconv. Last accessed 26 June 2026"},{"key":"11_CR12","doi-asserted-by":"crossref","unstructured":"Dai, A., Chang, A.X., Savva, M., Halber, M., Funkhouser, T., Nie\u00dfner, M.: Scannet: richly-annotated 3D reconstructions of indoor scenes. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5828\u20135839 (2017)","DOI":"10.1109\/CVPR.2017.261"},{"key":"11_CR13","doi-asserted-by":"crossref","unstructured":"He, S., Ding, H., Jiang, X., Wen, B.: Segpoint: segment any point cloud via large language model. In: ECCV, pp. 349\u2013367. Springer (2024)","DOI":"10.1007\/978-3-031-72670-5_20"},{"key":"11_CR14","unstructured":"Hu, E.J., Shen, Y., Wallis, P., Allen-Zhu, Z., Li, Y., Wang, S., Wang, L., Chen, W.: LoRA: low-rank adaptation of large language models. In: ICLR (2022)"},{"key":"11_CR15","doi-asserted-by":"crossref","unstructured":"Huang, J.: MLLM-For3D: Adapting Multimodal Large Language Model for 3D Reasoning Segmentation. NeurIPS (2025)","DOI":"10.52202\/085713-1839"},{"key":"11_CR16","doi-asserted-by":"crossref","unstructured":"Huang, K.C., Li, X., Qi, L., Yan, S., Yang, M.H.: Reason3D: Searching and Reasoning 3D Segmentation via Large Language Model (2024). arXiv preprint arXiv:2405.17427","DOI":"10.1109\/3DV66043.2025.00112"},{"issue":"2","key":"11_CR17","doi-asserted-by":"publisher","first-page":"1610","DOI":"10.1609\/aaai.v35i2.16253","volume":"35","author":"PH Huang","year":"2021","unstructured":"Huang, P.H., Lee, H.H., Chen, H.T., Liu, T.L.: Text-guided graph neural networks for referring 3D instance segmentation. AAAI 35(2), 1610\u20131618 (2021)","journal-title":"AAAI"},{"key":"11_CR18","doi-asserted-by":"crossref","unstructured":"Jain, A., Gkanatsios, N., Mediratta, I., Fragkiadaki, K.: Bottom Up Top Down Detection Transformers for Language Grounding in Images and Point Clouds (2021). arXiv:2112.08879 arXiv preprint","DOI":"10.1007\/978-3-031-20059-5_24"},{"key":"11_CR19","unstructured":"Kang, W., Qu, M., Kini, J., Wei, Y., Shah, M., Yan, Y.: Intent 3D: 3D Object Detection in RGB-D Scans Based on Human Intention (2024). arXiv:2405.18295 arXiv preprint"},{"key":"11_CR20","doi-asserted-by":"crossref","unstructured":"Kareem, A., Lahoud, J., Cholakkal, H.: Paris3D: reasoning-based 3D part segmentation using large multimodal model. In: European Conference on Computer Vision, pp. 466\u2013482. Springer (2024)","DOI":"10.1007\/978-3-031-73220-1_27"},{"key":"11_CR21","doi-asserted-by":"crossref","unstructured":"Li, R., Li, S., Kong, L., Yang, X., Liang, J.: Seeground: see and ground for zero-shot open-vocabulary 3D visual grounding. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 3707\u20133717 (2025)","DOI":"10.1109\/CVPR52734.2025.00351"},{"key":"11_CR22","doi-asserted-by":"crossref","unstructured":"Liang, Z., Li, Z., Xu, S., Tan, M., Jia, K.: Instance segmentation in 3D scenes using semantic superpoint tree networks. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2783\u20132792 (2021)","DOI":"10.1109\/ICCV48922.2021.00278"},{"key":"11_CR23","doi-asserted-by":"crossref","unstructured":"Liu, M., Zhu, Y., Cai, H., Han, S., Ling, Z., Porikli, F., Su, H.: Partslip: low-shot part segmentation for 3D point clouds via pretrained image-language models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 21736\u201321746 (2023)","DOI":"10.1109\/CVPR52729.2023.02082"},{"key":"11_CR24","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: International Conference on Learning Representations (2019)"},{"key":"11_CR25","unstructured":"Ma, X., Yong, S., Zheng, Z., Li, Q., Liang, Y., Zhu, S.C., Huang, S.: SQA3D: situated question answering in 3D scenes. In: International Conference on Learning Representations (2023)"},{"key":"11_CR26","doi-asserted-by":"crossref","unstructured":"Milletari, F., Navab, N., Ahmadi, S.A.: V-net: Fully convolutional neural networks for volumetric medical image segmentation. In: Fourth International Conference on 3D Vision (3DV), pp. 565\u2013571. IEEE (2016)","DOI":"10.1109\/3DV.2016.79"},{"key":"11_CR27","doi-asserted-by":"crossref","unstructured":"Nguyen, P., Ngo, T.D., Kalogerakis, E., Gan, C., Tran, A., Pham, C., Nguyen, K.: Open3DIS: Open-vocabulary 3D instance segmentation with 2D mask guidance. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4018\u20134028 (2024)","DOI":"10.1109\/CVPR52733.2024.00385"},{"key":"11_CR28","unstructured":"Ravi, N., Gabeur, V., Hu, Y.T., Hu, R., Ryali, C., Ma, T., Khedr, H., R\u00e4dle, R., Rolland, C., Gustafson, L., et\u00a0al.: SAM 2: Segment Anything in Images and Videos (2024). arXiv preprint arXiv:2408.00714"},{"key":"11_CR29","doi-asserted-by":"publisher","unstructured":"Ren, T., Liu, S., Zeng, A., Lin, J., Li, K., Cao, H., Chen, J., Huang, X., Chen, Y., Yan, F., Zeng, Z., Zhang, H., Li, F., Yang, J., Li, H., Jiang, Q., Zhang, L.: Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks (2024). https:\/\/doi.org\/10.48550\/arXiv.2401.14159","DOI":"10.48550\/arXiv.2401.14159"},{"key":"11_CR30","doi-asserted-by":"crossref","unstructured":"Robert, D., Raguet, H., Landrieu, L.: Efficient 3D semantic segmentation with superpoint transformer. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (2023)","DOI":"10.1109\/ICCV51070.2023.01577"},{"key":"11_CR31","unstructured":"Wang, Y., Ke, L., Zhang, B., Qu, T., Yu, H., Huang, Z., Yu, M., Xu, D., Yu, D.: N3D-VLM: Native 3D Grounding Enables Accurate Spatial Reasoning in Vision-Language Models (2025). arXiv preprint arXiv:2512.16561"},{"key":"11_CR32","doi-asserted-by":"crossref","unstructured":"Wu, C., Ma, Y., Chen, Q., Wang, H., Luo, G., Ji, J., Sun, X.: 3D-STMN: dependency-driven superpoint-text matching network for end-to-end 3D referring expression segmentation. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 38, pp. 5940\u20135948 (2024)","DOI":"10.1609\/aaai.v38i6.28408"},{"key":"11_CR33","doi-asserted-by":"crossref","unstructured":"Wu, Y., Cheng, X., Zhang, R., Cheng, Z., Zhang, J.: Eda: explicit text-decoupling and dense alignment for 3D visual grounding. In: CVPR, pp. 19231\u201319242 (2023)","DOI":"10.1109\/CVPR52729.2023.01843"},{"key":"11_CR34","unstructured":"Xu, B., Zhu, S., Jin, Z., Li, J., Wang, H.: S$$^2$$-MLLM: Boosting Spatial Reasoning Capability of MLLMS for 3D Visual Grounding with Structural Guidance (2025). arXiv:2512.01223 arXiv preprint"},{"key":"11_CR35","doi-asserted-by":"publisher","first-page":"59468","DOI":"10.52202\/079017-1899","volume":"37","author":"W Xu","year":"2024","unstructured":"Xu, W., Shi, C., Tu, S., Zhou, X., Liang, D., Bai, X.: A unified framework for 3D scene understanding. Adv. Neural. Inf. Process. Syst. 37, 59468\u201359490 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"11_CR36","doi-asserted-by":"crossref","unstructured":"Yeshwanth, C., Liu, Y.C., Nie\u00dfner, M., Dai, A.: Scannet++: a high-fidelity dataset of 3D indoor scenes. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 12\u201322 (2023)","DOI":"10.1109\/ICCV51070.2023.00008"},{"key":"11_CR37","doi-asserted-by":"crossref","unstructured":"Yu, H., Li, W., Wang, S., Chen, J., Zhu, J.: Inst3d-LMM: instance-aware 3D scene understanding with multi-modal instruction tuning. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 14147\u201314157 (2025)","DOI":"10.1109\/CVPR52734.2025.01320"},{"key":"11_CR38","doi-asserted-by":"crossref","unstructured":"Yuan, Z., Yan, X., Liao, Y., Zhang, R., Wang, S., Li, Z., Cui, S.: Instancerefer: cooperative holistic understanding for visual grounding on point clouds through instance multi-level contextual referring. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 1791\u20131800 (2021)","DOI":"10.1109\/ICCV48922.2021.00181"},{"key":"11_CR39","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Gong, Z., Chang, A.X.: Multi3drefer: grounding text description to multiple 3D objects. In: ICCV, pp. 15225\u201315236 (2023)","DOI":"10.1109\/ICCV51070.2023.01397"}],"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\/978-3-032-37461-5_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T06:34:54Z","timestamp":1790231694000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37461-5_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032374608","9783032374615"],"references-count":39,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37461-5_11","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":"25 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"}}]}}