{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T07:07:17Z","timestamp":1788937637044,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":113,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032372512","type":"print"},{"value":"9783032372529","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\/978-3-032-37252-9_18","type":"book-chapter","created":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T06:46:47Z","timestamp":1788936407000},"page":"312-333","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Cambrian-P: Pose-Grounded Video Understanding"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-1723-3563","authenticated-orcid":false,"given":"Jihan","family":"Yang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-9255-016X","authenticated-orcid":false,"given":"Zifan","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8308-841X","authenticated-orcid":false,"given":"Xichen","family":"Pan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-0379-3445","authenticated-orcid":false,"given":"Shusheng","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9291-3098","authenticated-orcid":false,"given":"Junyi","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hu","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0656-9874","authenticated-orcid":false,"given":"Shang-Wen","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-5567-1164","authenticated-orcid":false,"given":"Saining","family":"Xie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,10]]},"reference":[{"key":"18_CR1","unstructured":"Achiam, J., et al.: GPT-4 technical report. arXiv preprint arXiv:2303.08774 (2023)"},{"key":"18_CR2","doi-asserted-by":"crossref","unstructured":"Agrawal, H., et al.: Nocaps: novel object captioning at scale. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00904"},{"key":"18_CR3","doi-asserted-by":"crossref","unstructured":"Antequera, M.L., Gargallo, P., Hofinger, M., Bulo, S.R., Kuang, Y., Kontschieder, P.: Mapillary planet-scale depth dataset. In: ECCV (2020)","DOI":"10.1007\/978-3-030-58536-5_35"},{"key":"18_CR4","doi-asserted-by":"crossref","unstructured":"Armeni, I., et al.: 3D semantic parsing of large-scale indoor spaces. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.170"},{"key":"18_CR5","unstructured":"Bai, J., et\u00a0al.: Qwen technical report. arXiv preprint arXiv:2309.16609 (2023)"},{"key":"18_CR6","unstructured":"Bai, J., et al.: Qwen-VL: a frontier large vision-language model with versatile abilities. arXiv preprint arXiv:2308.12966 (2023)"},{"key":"18_CR7","unstructured":"Bai, S., et al.: Qwen3-VL technical report. arXiv preprint arXiv:2511.21631 (2025)"},{"key":"18_CR8","unstructured":"Bai, S., et\u00a0al.: Qwen2.5-VL technical report. arXiv preprint arXiv:2502.13923 (2025)"},{"key":"18_CR9","unstructured":"Baruch, G., et al.: ARKitscenes - a diverse real-world dataset for 3D indoor scene understanding using mobile RGB-d data. In: NeurIPS (2021)"},{"key":"18_CR10","unstructured":"Brown, E., Ray, A., Krishna, R., Girshick, R., Fergus, R., Xie, S.: SIMS-V: simulated instruction-tuning for spatial video understanding. arXiv preprint arXiv:2511.04668 (2025)"},{"key":"18_CR11","unstructured":"Brown, T., et al.: Language models are few-shot learners. In: NeurIPS (2020)"},{"key":"18_CR12","doi-asserted-by":"crossref","unstructured":"Butler, D.J., Wulff, J., Stanley, G.B., Black, M.J.: A naturalistic open source movie for optical flow evaluation. In: ECCV (2012)","DOI":"10.1007\/978-3-642-33783-3_44"},{"key":"18_CR13","unstructured":"Cadena, C., et al.: Past, present, and future of simultaneous localization and mapping: toward the robust-perception age. T-RO (2017)"},{"key":"18_CR14","unstructured":"Cai, Z., et\u00a0al.: Scaling spatial intelligence with multimodal foundation models. arXiv preprint arXiv:2511.13719 (2025)"},{"key":"18_CR15","doi-asserted-by":"crossref","unstructured":"Chen, B., et al.: SpatialVLM: endowing vision-language models with spatial reasoning capabilities. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.01370"},{"key":"18_CR16","doi-asserted-by":"crossref","unstructured":"Chen, G., et\u00a0al.: Eagle 2.5: boosting long-context post-training for frontier vision-language models. In: NeurIPS (2025)","DOI":"10.52202\/085713-3047"},{"key":"18_CR17","unstructured":"Chen, X., et al.: Microsoft COCO captions: data collection and evaluation server. arXiv preprint arXiv:1504.00325 (2015)"},{"key":"18_CR18","doi-asserted-by":"crossref","unstructured":"Chen, Z., et\u00a0al.: INTERNVL: scaling up vision foundation models and aligning for generic visual-linguistic tasks. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.02283"},{"key":"18_CR19","unstructured":"Comanici, G., et al.: Gemini 2.5: pushing the frontier with advanced reasoning, multimodality, long context, and next generation agentic capabilities. arXiv preprint arXiv:2507.06261 (2025)"},{"key":"18_CR20","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: CVPR (2017)","DOI":"10.1109\/CVPR.2017.261"},{"key":"18_CR21","doi-asserted-by":"crossref","unstructured":"Deitke, M., et al.: ProcTHOR: large-scale embodied ai using procedural generation. In: NeurIPS (2022)","DOI":"10.52202\/068431-0433"},{"key":"18_CR22","unstructured":"Fan, Z., et\u00a0al.: VLM-3R: vision-language models augmented with instruction-aligned 3D reconstruction. In: CVPR (2026)"},{"key":"18_CR23","doi-asserted-by":"crossref","unstructured":"Furukawa, Y., Ponce, J.: Accurate, dense, and robust multiview stereopsis. TPAMI (2009)","DOI":"10.1109\/TPAMI.2009.161"},{"key":"18_CR24","unstructured":"Grattafiori, A., et al.: The LLaMA 3 herd of models. arXiv preprint arXiv:2407.21783 (2024)"},{"key":"18_CR25","doi-asserted-by":"crossref","unstructured":"Hartley, R., Zisserman, A.: Multiple View Geometry in Computer Vision. Cambridge University Press (2003)","DOI":"10.1017\/CBO9780511811685"},{"key":"18_CR26","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., Girshick, R.: Masked autoencoders are scalable vision learners. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"18_CR27","unstructured":"Hu, K., et al.: Video-MMMU: evaluating knowledge acquisition from multi-discipline professional videos. arXiv preprint arXiv:2501.13826 (2025)"},{"key":"18_CR28","unstructured":"Hu, W., et al.: G$$^2$$VLM: geometry grounded vision language model with unified 3d reconstruction and spatial reasoning. arXiv preprint arXiv:2511.21688 (2025)"},{"key":"18_CR29","doi-asserted-by":"crossref","unstructured":"Hu, Y.T., Wang, J., Yeh, R.A., Schwing, A.G.: SAIL-VOS 3D: a synthetic dataset and baselines for object detection and 3D mesh reconstruction from video data. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00147"},{"key":"18_CR30","unstructured":"Huang, J., et al.: ViPE: video pose engine for 3D geometric perception. arXiv preprint arXiv:2508.10934 (2025)"},{"key":"18_CR31","doi-asserted-by":"crossref","unstructured":"Huang, P.H., Matzen, K., Kopf, J., Ahuja, N., Huang, J.B.: DeepMVS: learning multi-view stereopsis. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00298"},{"key":"18_CR32","unstructured":"Hurst, A., et al.: GPT-4O system card. arXiv preprint arXiv:2410.21276 (2024)"},{"key":"18_CR33","doi-asserted-by":"crossref","unstructured":"Karaev, N., Rocco, I., Graham, B., Neverova, N., Vedaldi, A., Rupprecht, C.: DynamicStereo: consistent dynamic depth from stereo videos. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01271"},{"key":"18_CR34","doi-asserted-by":"crossref","unstructured":"Keetha, N., et al.: MapAnything: universal feed-forward metric 3D reconstruction. arXiv preprint arXiv:2509.13414 (2025)","DOI":"10.1109\/3DV69130.2026.00054"},{"key":"18_CR35","doi-asserted-by":"crossref","unstructured":"Kerbl, B., Kopanas, G., Leimk\u00fchler, T., Drettakis, G., et al.: 3D gaussian splatting for real-time radiance field rendering. ACM Trans. Graph. (2023)","DOI":"10.1145\/3592433"},{"key":"18_CR36","unstructured":"Kim, M.J., et al.: OpenVLA: an open-source vision-language-action model. arXiv preprint arXiv:2406.09246 (2024)"},{"key":"18_CR37","unstructured":"Li, B., et\u00a0al.: LLaVA-onevision: easy visual task transfer. TMLR (2025)"},{"key":"18_CR38","unstructured":"Li, H., et al.: Thinking with geometry: active geometry integration for spatial reasoning. arXiv preprint arXiv:2602.06037 (2026)"},{"key":"18_CR39","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: ICML (2023)"},{"key":"18_CR40","doi-asserted-by":"crossref","unstructured":"Li, K., et\u00a0al.: MVbench: a comprehensive multi-modal video understanding benchmark. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.02095"},{"key":"18_CR41","doi-asserted-by":"crossref","unstructured":"Li, Z., Snavely, N.: MegaDepth: learning single-view depth prediction from internet photos. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00218"},{"key":"18_CR42","unstructured":"Li, Z., et\u00a0al.: Eagle 2: building post-training data strategies from scratch for frontier vision-language models. arXiv preprint arXiv:2501.14818 (2025)"},{"key":"18_CR43","unstructured":"Lin, H., et al.: Depth anything 3: recovering the visual space from any views. arXiv preprint arXiv:2511.10647 (2025)"},{"key":"18_CR44","unstructured":"Lin, J., et\u00a0al.: MMSI-video-bench: a holistic benchmark for video-based spatial intelligence. arXiv preprint arXiv:2512.10863 (2025)"},{"key":"18_CR45","doi-asserted-by":"crossref","unstructured":"Ling, L., et\u00a0al.: DL3DV-10K: a large-scale scene dataset for deep learning-based 3D vision. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.02092"},{"key":"18_CR46","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, C., Li, Y., Lee, Y.J.: Improved baselines with visual instruction tuning. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"18_CR47","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":"18_CR48","unstructured":"Liu, Y., et al.: Spatial-SSRL: enhancing spatial understanding via self-supervised reinforcement learning. arXiv preprint arXiv:2510.27606 (2025)"},{"key":"18_CR49","doi-asserted-by":"crossref","unstructured":"Longuet-Higgins, H.C.: A computer algorithm for reconstructing a scene from two projections. Nature (1981)","DOI":"10.1038\/293133a0"},{"key":"18_CR50","unstructured":"Lu, P., et al.: MathVista: evaluating mathematical reasoning of foundation models in visual contexts. In: ICLR (2024)"},{"key":"18_CR51","unstructured":"Ma, Y., Soatto, S., Kosecka, J., Sastry, S.S.: An Invitation to 3-D Vision: From Images to Geometric Models. Springer (2005)"},{"key":"18_CR52","doi-asserted-by":"crossref","unstructured":"Mangalam, K., Akshulakov, R., Malik, J.: EgoSchema: a diagnostic benchmark for very long-form video language understanding. In: NeurIPS (2023)","DOI":"10.52202\/075280-2004"},{"key":"18_CR53","doi-asserted-by":"crossref","unstructured":"Mehl, L., Schmalfuss, J., Jahedi, A., Nalivayko, Y., Bruhn, A.: Spring: a high-resolution high-detail dataset and benchmark for scene flow, optical flow and stereo. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00482"},{"key":"18_CR54","doi-asserted-by":"crossref","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 (2021)","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"18_CR55","doi-asserted-by":"crossref","unstructured":"Mur-Artal, R., Montiel, J.M.M., Tardos, J.D.: Orb-SLAM: a versatile and accurate monocular slam system. T-RO (2015)","DOI":"10.1109\/TRO.2015.2463671"},{"key":"18_CR56","doi-asserted-by":"crossref","unstructured":"Murai, R., Dexheimer, E., Davison, A.J.: MASt3R-SLAM: real-time dense slam with 3D reconstruction priors. In: CVPR (2025)","DOI":"10.1109\/CVPR52734.2025.01556"},{"key":"18_CR57","unstructured":"Nist\u00e9r, D., Naroditsky, O., Bergen, J.: Visual odometry. In: CVPR (2004)"},{"key":"18_CR58","unstructured":"Oquab, M., et al.: DINOv2: learning robust visual features without supervision. arXiv preprint arXiv:2304.07193 (2023)"},{"key":"18_CR59","unstructured":"Ouyang, K., et al.: Spacer: reinforcing MLLMs in video spatial reasoning. arXiv preprint arXiv:2504.01805 (2025)"},{"key":"18_CR60","doi-asserted-by":"crossref","unstructured":"Patraucean, V., et al.: Perception test: a diagnostic benchmark for multimodal video models. In: NeurIPS (2023)","DOI":"10.52202\/075280-1852"},{"key":"18_CR61","doi-asserted-by":"crossref","unstructured":"Qin, T., Li, P., Shen, S.: VINS-mono: a robust and versatile monocular visual-inertial state estimator. T-RO (2018)","DOI":"10.1109\/TRO.2018.2853729"},{"key":"18_CR62","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: ICML (2021)"},{"key":"18_CR63","unstructured":"Ramakrishnan, S.K., Wijmans, E., Kraehenbuehl, P., Koltun, V.: Does spatial cognition emerge in frontier models? In: ICLR (2025)"},{"key":"18_CR64","doi-asserted-by":"crossref","unstructured":"Ren, S., Yao, L., Li, S., Sun, X., Hou, L.: TimeChat: a time-sensitive multimodal large language model for long video understanding. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.01357"},{"key":"18_CR65","doi-asserted-by":"crossref","unstructured":"Roberts, M., et al.: HyperSim: a photorealistic synthetic dataset for holistic indoor scene understanding. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01073"},{"key":"18_CR66","doi-asserted-by":"crossref","unstructured":"Saikh, T., Ghosal, T., Mittal, A., Ekbal, A., Bhattacharyya, P.: ScienceQA: a novel resource for question answering on scholarly articles. In: IJDL (2022)","DOI":"10.1007\/s00799-022-00329-y"},{"key":"18_CR67","doi-asserted-by":"crossref","unstructured":"Schonberger, J.L., Frahm, J.M.: Structure-from-motion revisited. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.445"},{"key":"18_CR68","doi-asserted-by":"crossref","unstructured":"Schops, T., et al.: A multi-view stereo benchmark with high-resolution images and multi-camera videos. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.272"},{"key":"18_CR69","unstructured":"Seitz, S.M., Curless, B., Diebel, J., Scharstein, D., Szeliski, R.: A comparison and evaluation of multi-view stereo reconstruction algorithms. In: CVPR (2006)"},{"key":"18_CR70","unstructured":"Shangguan, Z., et al.: Tomato: assessing visual temporal reasoning capabilities in multimodal foundation models. In: ICLR (2025)"},{"key":"18_CR71","doi-asserted-by":"crossref","unstructured":"Song, E., et\u00a0al.: MovieChat: from dense token to sparse memory for long video understanding. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.01725"},{"key":"18_CR72","doi-asserted-by":"crossref","unstructured":"Sturm, J., Engelhard, N., Endres, F., Burgard, W., Cremers, D.: A benchmark for the evaluation of RGB-D SLAM systems. In: IROS (2012)","DOI":"10.1109\/IROS.2012.6385773"},{"key":"18_CR73","doi-asserted-by":"crossref","unstructured":"Szeliski, R.: Computer Vision: Algorithms and Applications. Springer (2022)","DOI":"10.1007\/978-3-030-34372-9"},{"key":"18_CR74","unstructured":"Team, G., et al.: Gemini: a family of highly capable multimodal models. arXiv preprint arXiv:2312.11805 (2023)"},{"key":"18_CR75","unstructured":"Team, G., et al.: Gemini 1.5: unlocking multimodal understanding across millions of tokens of context. arXiv preprint arXiv:2403.05530 (2024)"},{"key":"18_CR76","unstructured":"Team, G.R., et al.: Gemini robotics: bringing ai into the physical world. arXiv preprint arXiv:2503.20020 (2025)"},{"key":"18_CR77","doi-asserted-by":"crossref","unstructured":"Tong, P., et al.: Cambrian-1: a fully open, vision-centric exploration of multimodal LLMs. In: NeurIPS (2024)","DOI":"10.52202\/079017-2771"},{"key":"18_CR78","doi-asserted-by":"crossref","unstructured":"Tosi, F., Liao, Y., Schmitt, C., Geiger, A.: SMD-nets: stereo mixture density networks. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00883"},{"key":"18_CR79","unstructured":"Touvron, H., et al.: LLaMA: open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)"},{"key":"18_CR80","unstructured":"Touvron, H., et al.: LLaMA 2: open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)"},{"key":"18_CR81","unstructured":"Tschannen, M., et al.: SigLip 2: multilingual vision-language encoders with improved semantic understanding, localization, and dense features. arXiv preprint arXiv:2502.14786 (2025)"},{"key":"18_CR82","doi-asserted-by":"crossref","unstructured":"Van Hoorick, B., et al.: Generative camera dolly: extreme monocular dynamic novel view synthesis. In: ECCV (2024)","DOI":"10.1007\/978-3-031-72691-0_18"},{"key":"18_CR83","doi-asserted-by":"crossref","unstructured":"Wang, H., Agapito, L.: 3D reconstruction with spatial memory. In: 3DV (2025)","DOI":"10.1109\/3DV66043.2025.00013"},{"key":"18_CR84","doi-asserted-by":"crossref","unstructured":"Wang, J., Chen, M., Karaev, N., Vedaldi, A., Rupprecht, C., Novotny, D.: VGGT: visual geometry grounded transformer. In: CVPR (2025)","DOI":"10.1109\/CVPR52734.2025.00499"},{"key":"18_CR85","unstructured":"Wang, P., et\u00a0al.: Qwen2-VL: enhancing vision-language model\u2019s perception of the world at any resolution. arXiv preprint arXiv:2409.12191 (2024)"},{"key":"18_CR86","doi-asserted-by":"crossref","unstructured":"Wang, Q., Zhang, Y., Holynski, A., Efros, A.A., Kanazawa, A.: Continuous 3D perception model with persistent state. In: CVPR (2025)","DOI":"10.1109\/CVPR52734.2025.00983"},{"key":"18_CR87","doi-asserted-by":"crossref","unstructured":"Wang, S., Leroy, V., Cabon, Y., Chidlovskii, B., Revaud, J.: DUSt3R: geometric 3D vision made easy. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.01956"},{"key":"18_CR88","doi-asserted-by":"crossref","unstructured":"Wang, W., et al.: TartanAir: a dataset to push the limits of visual slam. In: IROS (2020)","DOI":"10.1109\/IROS45743.2020.9341801"},{"key":"18_CR89","unstructured":"Wang, Y., et al.: $$\\pi ^{3}$$: permutation-equivariant visual geometry learning. In: ICLR (2026). https:\/\/openreview.net\/forum?id=DTQIjngDta"},{"key":"18_CR90","doi-asserted-by":"crossref","unstructured":"Wu, Y., Zheng, W., Zhou, J., Lu, J.: Point3R: streaming 3D reconstruction with explicit spatial pointer memory. arXiv preprint arXiv:2507.02863 (2025)","DOI":"10.52202\/085713-2344"},{"key":"18_CR91","unstructured":"Yang, A., et\u00a0al.: Qwen2.5 technical report. arXiv preprint arXiv:2412.15115 (2024)"},{"key":"18_CR92","doi-asserted-by":"crossref","unstructured":"Yang, J., et al.: Fast3R: towards 3D reconstruction of 1000+ images in one forward pass. In: CVPR (2025)","DOI":"10.1109\/CVPR52734.2025.02042"},{"key":"18_CR93","doi-asserted-by":"crossref","unstructured":"Yang, J., Ding, R., Brown, E., Qi, X., Xie, S.: V-IRL: grounding virtual intelligence in real life. In: ECCV (2024)","DOI":"10.1007\/978-3-031-72995-9_3"},{"key":"18_CR94","doi-asserted-by":"crossref","unstructured":"Yang, J., Yang, S., Gupta, A., Han, R., Fei-Fei, L., Xie, S.: Thinking in space: how multimodal large language models see, remember and recall spaces. In: CVPR (2024)","DOI":"10.1109\/CVPR52734.2025.00994"},{"key":"18_CR95","unstructured":"Yang, R., et\u00a0al.: Visual spatial tuning. arXiv preprint arXiv:2511.05491 (2025)"},{"key":"18_CR96","unstructured":"Yang, S., et al.: Towards spatial supersensing in video. In: ICLR (2026)"},{"key":"18_CR97","unstructured":"Yang, S., et\u00a0al.: MMSI-bench: a benchmark for multi-image spatial intelligence. arXiv preprint arXiv:2505.23764 (2025)"},{"key":"18_CR98","doi-asserted-by":"crossref","unstructured":"Yao, Y., Luo, Z., Li, S., Fang, T., Quan, L.: MVSNet: depth inference for unstructured multi-view stereo. In: ECCV (2018)","DOI":"10.1007\/978-3-030-01237-3_47"},{"key":"18_CR99","doi-asserted-by":"crossref","unstructured":"Yao, Y., et al.: BlendedMVS: a large-scale dataset for generalized multi-view stereo networks. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00186"},{"key":"18_CR100","unstructured":"Yeh, C.H., et al.: Seeing from another perspective: evaluating multi-view understanding in MLLMs. arXiv preprint arXiv:2504.15280 (2025)"},{"key":"18_CR101","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: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00008"},{"key":"18_CR102","unstructured":"Yin, B., et\u00a0al.: Spatial mental modeling from limited views. In: ICLR (2026)"},{"key":"18_CR103","doi-asserted-by":"crossref","unstructured":"Yue, X., et\u00a0al.: MMMU: a massive multi-discipline multimodal understanding and reasoning benchmark for expert AGI. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.00913"},{"key":"18_CR104","doi-asserted-by":"crossref","unstructured":"Yue, X., et\u00a0al.: MMMU-pro: a more robust multi-discipline multimodal understanding benchmark. In: ACL (2025)","DOI":"10.18653\/v1\/2025.acl-long.736"},{"key":"18_CR105","doi-asserted-by":"crossref","unstructured":"Zhai, X., Mustafa, B., Kolesnikov, A., Beyer, L.: Sigmoid loss for language image pre-training. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"18_CR106","doi-asserted-by":"crossref","unstructured":"Zhang, J., et\u00a0al.: From flatland to space: teaching vision-language models to perceive and reason in 3D. arXiv preprint arXiv:2503.22976 (2025)","DOI":"10.52202\/085713-5180"},{"key":"18_CR107","unstructured":"Zhang, J., et al.: MonST3r: a simple approach for estimating geometry in the presence of motion. In: ICLR (2025). https:\/\/openreview.net\/forum?id=lJpqxFgWCM"},{"key":"18_CR108","doi-asserted-by":"crossref","unstructured":"Zhang, S., et al.: Flare: feed-forward geometry, appearance and camera estimation from uncalibrated sparse views. In: CVPR (2025)","DOI":"10.1109\/CVPR52734.2025.02043"},{"key":"18_CR109","unstructured":"Zhang, Y., et al.: Video instruction tuning with synthetic data. TMLR (2025)"},{"key":"18_CR110","doi-asserted-by":"crossref","unstructured":"Zhang, Y., et al.: UFM: a simple path towards unified dense correspondence with flow. arXiv preprint arXiv:2506.09278 (2025)","DOI":"10.52202\/085713-3648"},{"key":"18_CR111","doi-asserted-by":"crossref","unstructured":"Zheng, D., Huang, S., Li, Y., Wang, L.: Learning from videos for 3D world: enhancing MLLMs with 3D vision geometry priors. In: NeurIPS (2025). https:\/\/openreview.net\/forum?id=oUYmk8WaG0","DOI":"10.52202\/085713-0693"},{"key":"18_CR112","unstructured":"Zhu, J., et al.: InternVL3: exploring advanced training and test-time recipes for open-source multimodal models. arXiv preprint arXiv:2504.10479 (2025)"},{"key":"18_CR113","unstructured":"Zhuo, D., Zheng, W., Guo, J., Wu, Y., Zhou, J., Lu, J.: Streaming visual geometry transformer. In: ICLR (2026). https:\/\/openreview.net\/forum?id=5APgTKsnx8"}],"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\/978-3-032-37252-9_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T06:47:07Z","timestamp":1788936427000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37252-9_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032372512","9783032372529"],"references-count":113,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37252-9_18","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":"10 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"}}]}}