{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T06:07:08Z","timestamp":1788934028241,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":107,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032373687","type":"print"},{"value":"9783032373694","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\/978-3-032-37369-4_34","type":"book-chapter","created":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T05:46:09Z","timestamp":1788932769000},"page":"628-647","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Argus: Metric Panoramic 3D Reconstruction for\u00a0Indoor Scenes"],"prefix":"10.1007","author":[{"given":"Xi","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Linyuan","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yan","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tong","family":"Rao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kai","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinchen","family":"Hui","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cihui","family":"Pan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,10]]},"reference":[{"key":"34_CR1","doi-asserted-by":"crossref","unstructured":"Agarwal, S., Snavely, N., Simon, I., Seitz, S.M., Szeliski, R.: Building Rome in a day. In: ICCV (2009)","DOI":"10.1109\/ICCV.2009.5459148"},{"key":"34_CR2","doi-asserted-by":"crossref","unstructured":"Ai, H., Cao, Z., Wang, L.: A survey of representation learning, optimization strategies, and applications for omnidirectional vision: H. Ai et al. IJCV 133(8), 4973\u20135012 (2025)","DOI":"10.1007\/s11263-025-02391-w"},{"key":"34_CR3","doi-asserted-by":"crossref","unstructured":"Alama, O., et al.: RayFronts: open-set semantic ray frontiers for online scene understanding and exploration. In: IROS, pp, 5930\u20135937 (2025)","DOI":"10.1109\/IROS60139.2025.11245813"},{"key":"34_CR4","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, pp. 589\u2013604 (2020)","DOI":"10.1007\/978-3-030-58536-5_35"},{"key":"34_CR5","unstructured":"Armeni, I., Sax, S., Zamir, A.R., Savarese, S.: Joint 2D-3D-semantic data for indoor scene understanding. arXiv preprint: arXiv:1702.01105 (2017)"},{"key":"34_CR6","doi-asserted-by":"crossref","unstructured":"Barath, D., Matas, J.: Graph-Cut RANSAC. In: CVPR, pp. 6733\u20136741 (2018)","DOI":"10.1109\/CVPR.2018.00704"},{"key":"34_CR7","doi-asserted-by":"crossref","unstructured":"Besl, P.J., McKay, N.D.: Method for registration of 3-D shapes. In: Sensor Fusion IV: Control Paradigms and Data Structures, vol.\u00a01611, pp. 586\u2013606. SPIE (1992)","DOI":"10.1117\/12.57955"},{"key":"34_CR8","doi-asserted-by":"crossref","unstructured":"Bian, J., Lin, W.Y., Matsushita, Y., Yeung, S.K., Nguyen, T.D., Cheng, M.M.: GMS: grid-based motion statistics for fast, ultra-robust feature correspondence. In: CVPR, pp. 4181\u20134190 (2017)","DOI":"10.1109\/CVPR.2017.302"},{"key":"34_CR9","unstructured":"Cabon, Y., Murray, N., Humenberger, M.: Virtual KITTI 2. arXiv preprint: arXiv:2001.10773 (2020)"},{"key":"34_CR10","doi-asserted-by":"crossref","unstructured":"Campos, C., Elvira, R., Rodr\u00edguez, J.J.G., Montiel, J.M., Tard\u00f3s, J.D.: ORB-SLAM3: an accurate open-source library for visual, visual-inertial, and multimap slam. IEEE Trans. Rob. (2021)","DOI":"10.1109\/TRO.2021.3075644"},{"key":"34_CR11","doi-asserted-by":"crossref","unstructured":"Cao, Z., et al.: PanDA: towards panoramic depth anything with unlabeled panoramas and mobius spatial augmentation. In: CVPR (2025)","DOI":"10.1109\/CVPR52734.2025.00100"},{"key":"34_CR12","doi-asserted-by":"crossref","unstructured":"Chang, A., et al.: Matterport3D: learning from RGB-D data in indoor environments. In: 3DV (2017)","DOI":"10.1109\/3DV.2017.00081"},{"key":"34_CR13","unstructured":"Chen, X., Chen, Y., Xiu, Y., Geiger, A., Chen, A.: TTT3R: 3D reconstruction as test-time training. arXiv preprint: arXiv:2509.26645 (2025)"},{"key":"34_CR14","doi-asserted-by":"crossref","unstructured":"Cruz, S., Hutchcroft, W., Li, Y., Khosravan, N., Boyadzhiev, I., Kang, S.B.: Zillow indoor dataset: annotated floor plans with 360deg panoramas and 3D room layouts. In: CVPR, pp. 2133\u20132143 (2021)","DOI":"10.1109\/CVPR46437.2021.00217"},{"key":"34_CR15","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"},{"issue":"4","key":"34_CR16","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3072959.3054739","volume":"36","author":"A Dai","year":"2017","unstructured":"Dai, A., Nie\u00dfner, M., Zollh\u00f6fer, M., Izadi, S., Theobalt, C.: BundleFusion: real-time globally consistent 3D reconstruction using on-the-fly surface reintegration. ToG 36(4), 1 (2017)","journal-title":"ToG"},{"key":"34_CR17","doi-asserted-by":"crossref","unstructured":"Dao, T., Fu, D., Ermon, S., Rudra, A., R\u00e9, C.: FLASHATTENTION: fast and memory-efficient exact attention with io-awareness. In: NeurIPS (2022)","DOI":"10.52202\/068431-1189"},{"key":"34_CR18","unstructured":"Darcet, T., Oquab, M., Mairal, J., Bojanowski, P.: Vision transformers need registers. arXiv preprint: arXiv:2309.16588 (2023)"},{"key":"34_CR19","doi-asserted-by":"crossref","unstructured":"Deitke, M., et al.: Objaverse: a universe of annotated 3D objects. In: CVPR, pp. 13142\u201313153 (2023)","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"34_CR20","unstructured":"Deng, J., et al.: SAIL-Recon: large SFM by augmenting scene regression with localization. arXiv preprint: arXiv:2508.17972 (2025)"},{"key":"34_CR21","doi-asserted-by":"crossref","unstructured":"DeTone, D., Malisiewicz, T., Rabinovich, A.: SuperPoint: self-supervised interest point detection and description. In: CVPRW (2018)","DOI":"10.1109\/CVPRW.2018.00060"},{"issue":"1","key":"34_CR22","doi-asserted-by":"publisher","first-page":"269","DOI":"10.1007\/BF01386390","volume":"1","author":"E Dijkstra","year":"1959","unstructured":"Dijkstra, E.: A note on two problems in connexion with graphs. Numer. Math. 1(1), 269\u2013271 (1959)","journal-title":"Numer. Math."},{"key":"34_CR23","doi-asserted-by":"crossref","unstructured":"Duisterhof, B.P., Zust, L., Weinzaepfel, P., Leroy, V., Cabon, Y., Revaud, J.: MAST3R-SfM: a fully-integrated solution for unconstrained structure-from-motion. In: 2025 International Conference on 3D Vision (3DV), pp. 1\u201310 (2025)","DOI":"10.1109\/3DV66043.2025.00008"},{"key":"34_CR24","doi-asserted-by":"crossref","unstructured":"Edstedt, J., Athanasiadis, I., Wadenb\u00e4ck, M., Felsberg, M.: DKM: dense kernelized feature matching for geometry estimation. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01704"},{"key":"34_CR25","doi-asserted-by":"crossref","unstructured":"Edstedt, J., Sun, Q., B\u00f6kman, G., Wadenb\u00e4ck, M., Felsberg, M.: RoMA: robust dense feature matching. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.01871"},{"key":"34_CR26","unstructured":"Fei, X., et al.: Driv3R: learning dense 4D reconstruction for autonomous driving. arXiv preprint: arXiv:2412.06777 (2024)"},{"key":"34_CR27","unstructured":"Feng, W., et\u00a0al.: Quantized visual geometry grounded transformer. arXiv preprint: arXiv:2509.21302 (2025)"},{"issue":"1\u20132","key":"34_CR28","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1561\/0600000052","volume":"9","author":"Y Furukawa","year":"2015","unstructured":"Furukawa, Y., Hern\u00e1ndez, C.: Multi-view stereo: a tutorial. Found. Trends Comput. Graph. Vis. 9(1\u20132), 1\u2013148 (2015)","journal-title":"Found. Trends Comput. Graph. Vis."},{"key":"34_CR29","doi-asserted-by":"crossref","unstructured":"Goesele, M., Curless, B., Seitz, S.M.: Multi-view stereo revisited. In: CVPR, vol. 2, pp. 2402\u20132409 (2006)","DOI":"10.1109\/CVPR.2006.199"},{"key":"34_CR30","unstructured":"Greff, K., et\u00a0al.: Kubric: a scalable dataset generator. In: CVPR, pp. 3749\u20133761 (2022)"},{"key":"34_CR31","doi-asserted-by":"crossref","unstructured":"Guo, Y., Garg, S., Miangoleh, S.M.H., Huang, X., Ren, L.: Depth any camera: zero-shot metric depth estimation from any camera. In: CVPR (2025)","DOI":"10.1109\/CVPR52734.2025.02514"},{"key":"34_CR32","doi-asserted-by":"crossref","unstructured":"Hartley, R., Zisserman, A.: Multiple View Geometry in Computer Vision. Cambridge University Press (2003)","DOI":"10.1017\/CBO9780511811685"},{"key":"34_CR33","doi-asserted-by":"crossref","unstructured":"Hausler, S., Garg, S., Xu, M., Milford, M., Fischer, T.: Patch-netVLAD: multi-scale fusion of locally-global descriptors for place recognition. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01392"},{"key":"34_CR34","doi-asserted-by":"crossref","unstructured":"He, X., et al.: Detector-free structure from motion. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.02040"},{"key":"34_CR35","unstructured":"Hu, Y., et\u00a0al.: Toward general-purpose robots via foundation models: a survey and meta-analysis. arXiv preprint: arXiv:2312.08782 (2023)"},{"key":"34_CR36","doi-asserted-by":"crossref","unstructured":"Huang, P.H., Matzen, K., Kopf, J., Ahuja, N., Huang, J.B.: DeepMVS: learning multi-view stereopsis. In: CVPR, pp. 2821\u20132830 (2018)","DOI":"10.1109\/CVPR.2018.00298"},{"key":"34_CR37","doi-asserted-by":"crossref","unstructured":"Jang, W., Weinzaepfel, P., Leroy, V., Agapito, L., Revaud, J.: Pow3R: empowering unconstrained 3D reconstruction with camera and scene priors. In: CVPR, pp. 1071\u20131081 (2025)","DOI":"10.1109\/CVPR52734.2025.00108"},{"key":"34_CR38","unstructured":"Jiang, H., Song, Z., Lou, Z., Xu, R., Tan, M.: Depth anything in $$360^{\\circ }$$: towards scale invariance in the wild. arXiv preprint: arXiv:2512.22819 (2025)"},{"issue":"6","key":"34_CR39","first-page":"1","volume":"44","author":"L Jiang","year":"2025","unstructured":"Jiang, L., et al.: AnySplat: feed-forward 3D Gaussian splatting from unconstrained views. TOG 44(6), 1\u201316 (2025)","journal-title":"TOG"},{"key":"34_CR40","doi-asserted-by":"crossref","unstructured":"Jiang, Y., et al.: VR-GS: a physical dynamics-aware interactive gaussian splatting system in virtual reality. In: ACM SIGGRAPH (2024)","DOI":"10.1145\/3641519.3657448"},{"key":"34_CR41","doi-asserted-by":"crossref","unstructured":"Jung, D., Choi, J., Lee, Y., Manocha, D.: IM360: large-scale indoor mapping with 360 cameras. In: ICCV (2025)","DOI":"10.1109\/ICCV51701.2025.02697"},{"key":"34_CR42","doi-asserted-by":"crossref","unstructured":"Karaev, N., Makarov, Y., Wang, J., Neverova, N., Vedaldi, A., Rupprecht, C.: CoTracker3: simpler and better point tracking by pseudo-labelling real videos. In: ICCV, pp. 6013\u20136022 (2025)","DOI":"10.1109\/ICCV51701.2025.00568"},{"key":"34_CR43","doi-asserted-by":"crossref","unstructured":"Karaev, N., Rocco, I., Graham, B., Neverova, N., Vedaldi, A., Rupprecht, C.: CoTracker: it is better to track together. In: ECCV, pp. 18\u201335 (2024)","DOI":"10.1007\/978-3-031-73033-7_2"},{"key":"34_CR44","doi-asserted-by":"crossref","unstructured":"Keetha, N., et al.: SplaTAM: splat track & map 3D Gaussians for dense RGB-D slam. In: CVPR, pp. 21357\u201321366 (2024)","DOI":"10.1109\/CVPR52733.2024.02018"},{"key":"34_CR45","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":"34_CR46","doi-asserted-by":"crossref","unstructured":"Kerbl, B., Kopanas, G., Leimk\u00fchler, T., Drettakis, G.: 3D Gaussian splatting for real-time radiance field rendering. TOG (2023)","DOI":"10.1145\/3592433"},{"key":"34_CR47","unstructured":"K\u00fcmmerle, C., Verdun, C.M., St\u00f6ger, D.: Iteratively reweighted least squares for basis pursuit with global linear convergence rate. In: NeurIPS, pp. 2873\u20132886 (2021)"},{"key":"34_CR48","unstructured":"Li, H., et al.: Da $$^{2}$$: depth anything in any direction. arXiv preprint: arXiv:2509.26618 (2025)"},{"key":"34_CR49","doi-asserted-by":"crossref","unstructured":"Li, X.: Multi-view canonical pose 3D human body reconstruction based on volumetric TSDF. In: ECCV, pp. 392\u2013397 (2022)","DOI":"10.1007\/978-3-031-25072-9_27"},{"key":"34_CR50","doi-asserted-by":"crossref","unstructured":"Li, X., Rao, T., Pan, C.: EDM: efficient deep feature matching. In: ICCV, pp. 26198\u201326208 (2025)","DOI":"10.1109\/ICCV51701.2025.02431"},{"key":"34_CR51","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":"34_CR52","unstructured":"Lin, H., et al.: Depth anything 3: recovering the visual space from any views. arXiv preprint: arXiv:2511.10647 (2025)"},{"key":"34_CR53","unstructured":"Lin, X., et al.: Depth any panoramas: a foundation model for panoramic depth estimation. arXiv preprint: arXiv:2512.16913 (2025)"},{"key":"34_CR54","doi-asserted-by":"crossref","unstructured":"Lindenberger, P., Sarlin, P.E., Pollefeys, M.: LightGlue: local feature matching at light speed. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.01616"},{"key":"34_CR55","doi-asserted-by":"crossref","unstructured":"Ling, L., et\u00a0al.: DL3DV-10K: a large-scale scene dataset for deep learning-based 3D vision. In: CVPR, pp. 22160\u201322169 (2024)","DOI":"10.1109\/CVPR52733.2024.02092"},{"key":"34_CR56","unstructured":"Liu, Y., et al.: WorldMirror: universal 3D world reconstruction with any-prior prompting. arXiv preprint: arXiv:2510.10726 (2025)"},{"key":"34_CR57","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint: arXiv:1711.05101 (2017)"},{"key":"34_CR58","doi-asserted-by":"crossref","unstructured":"Lowe, D.G.: Distinctive image features from scale-invariant keypoints. IJCV (2004)","DOI":"10.1023\/B:VISI.0000029664.99615.94"},{"key":"34_CR59","doi-asserted-by":"crossref","unstructured":"Ma, X., Wang, Z., Li, H., Zhang, P., Ouyang, W., Fan, X.: Accurate monocular 3D object detection via color-embedded 3D reconstruction for autonomous driving. In: ICCV, pp. 6851\u20136860 (2019)","DOI":"10.1109\/ICCV.2019.00695"},{"issue":"1","key":"34_CR60","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":"34_CR61","doi-asserted-by":"crossref","unstructured":"Moulon, P., Monasse, P., Perrot, R., Marlet, R.: OpenMVG: open multiple view geometry. In: International Workshop on Reproducible Research in Pattern Recognition, pp. 60\u201374. Springer (2016)","DOI":"10.1007\/978-3-319-56414-2_5"},{"key":"34_CR62","doi-asserted-by":"crossref","unstructured":"Mur-Artal, R., Montiel, J.M.M., Tardos, J.D.: ORB-SLAM: a versatile and accurate monocular slam system. IEEE Trans. Rob. (2015)","DOI":"10.1109\/TRO.2015.2463671"},{"key":"34_CR63","unstructured":"Oquab, M., et al.: DINOv2: learning robust visual features without supervision. arXiv preprint: arXiv:2304.07193 (2023)"},{"key":"34_CR64","doi-asserted-by":"crossref","unstructured":"Pan, X., et al.: Aria digital twin: a new benchmark dataset for egocentric 3D machine perception. In: ICCV, pp. 20133\u201320143 (2023)","DOI":"10.1109\/ICCV51070.2023.01842"},{"key":"34_CR65","doi-asserted-by":"crossref","unstructured":"Piccinelli, L., et al.: UniK3D: universal camera monocular 3D estimation. In: CVPR (2025)","DOI":"10.1109\/CVPR52734.2025.00104"},{"key":"34_CR66","doi-asserted-by":"crossref","unstructured":"Ranftl, R., Bochkovskiy, A., Koltun, V.: Vision transformers for dense prediction. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01196"},{"key":"34_CR67","doi-asserted-by":"crossref","unstructured":"Reizenstein, J., Shapovalov, R., Henzler, P., Sbordone, L., Labatut, P., Novotny, D.: Common objects in 3D: large-scale learning and evaluation of real-life 3D category reconstruction. In: ICCV, pp. 10901\u201310911 (2021)","DOI":"10.1109\/ICCV48922.2021.01072"},{"key":"34_CR68","doi-asserted-by":"crossref","unstructured":"Roberts, M., et al.: Hypersim: a photorealistic synthetic dataset for holistic indoor scene understanding. In: ICCV, pp. 10912\u201310922 (2021)","DOI":"10.1109\/ICCV48922.2021.01073"},{"key":"34_CR69","doi-asserted-by":"crossref","unstructured":"Rublee, E., Rabaud, V., Konolige, K., Bradski, G.: ORB: an efficient alternative to sift or surf. In: ICCV (2011)","DOI":"10.1109\/ICCV.2011.6126544"},{"key":"34_CR70","doi-asserted-by":"crossref","unstructured":"Sarlin, P.E., DeTone, D., Malisiewicz, T., Rabinovich, A.: SuperGlue: learning feature matching with graph neural networks. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00499"},{"key":"34_CR71","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":"34_CR72","doi-asserted-by":"crossref","unstructured":"Sch\u00f6nberger, J.L., Zheng, E., Frahm, J.M., Pollefeys, M.: Pixelwise view selection for unstructured multi-view stereo. In: ECCV, pp. 501\u2013518 (2016)","DOI":"10.1007\/978-3-319-46487-9_31"},{"key":"34_CR73","unstructured":"Seedream, T., et\u00a0al.: Seedream 4.0: toward next-generation multimodal image generation. arXiv preprint: arXiv:2509.20427 (2025)"},{"key":"34_CR74","doi-asserted-by":"crossref","unstructured":"Seitz, S.M., Curless, B., Diebel, J., Scharstein, D., Szeliski, R.: A comparison and evaluation of multi-view stereo reconstruction algorithms. In: CVPR, vol. 1, pp. 519\u2013528 (2006)","DOI":"10.1109\/CVPR.2006.19"},{"key":"34_CR75","unstructured":"Shen, Y., Zhang, Z., Qu, Y., Cao, L.: FastVGGT: training-free acceleration of visual geometry transformer. arXiv preprint: arXiv:2509.02560 (2025)"},{"key":"34_CR76","unstructured":"Straub, J., et al.: The replica dataset: a digital replica of indoor spaces. arXiv preprint: arXiv:1906.05797 (2019)"},{"key":"34_CR77","doi-asserted-by":"crossref","unstructured":"Sun, J., Shen, Z., Wang, Y., Bao, H., Zhou, X.: LoFTR: detector-free local feature matching with transformers. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00881"},{"key":"34_CR78","doi-asserted-by":"crossref","unstructured":"Sun, W., Jiang, W., Trulls, E., Tagliasacchi, A., Yi, K.M.: ACNe: attentive context normalization for robust permutation-equivariant learning. In: CVPR, pp. 11286\u201311295 (2020)","DOI":"10.1109\/CVPR42600.2020.01130"},{"key":"34_CR79","unstructured":"Szot, A., et al.: Habitat 2.0: Training home assistants to rearrange their habitat. In: NeurIPS, vol. 34, pp. 251\u2013266 (2021)"},{"key":"34_CR80","doi-asserted-by":"crossref","unstructured":"Taira, H., et al.: InLoc: indoor visual localization with dense matching and view synthesis. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00752"},{"key":"34_CR81","doi-asserted-by":"crossref","unstructured":"Triggs, B., McLauchlan, P.F., Hartley, R.I., Fitzgibbon, A.W.: Bundle adjustment\u2014a modern synthesis. In: International Workshop on Vision Algorithms (1999)","DOI":"10.1007\/3-540-44480-7_21"},{"issue":"4","key":"34_CR82","doi-asserted-by":"publisher","first-page":"376","DOI":"10.1109\/34.88573","volume":"13","author":"S Umeyama","year":"1991","unstructured":"Umeyama, S.: Least-squares estimation of transformation parameters between two point patterns. PAMI 13(4), 376\u2013380 (1991)","journal-title":"PAMI"},{"key":"34_CR83","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NeurIPS (2017)"},{"key":"34_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":"34_CR85","unstructured":"Wang, J., et al.: VGGT-$$\\omega $$. arXiv preprint: arXiv:2605.15195 (2026)"},{"key":"34_CR86","doi-asserted-by":"crossref","unstructured":"Wang, J., Karaev, N., Rupprecht, C., Novotny, D.: VGGSfM: visual geometry grounded deep structure from motion. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.02049"},{"key":"34_CR87","doi-asserted-by":"crossref","unstructured":"Wang, R., et al.: MoGe: unlocking accurate monocular geometry estimation for open-domain images with optimal training supervision. In: CVPR (2025)","DOI":"10.1109\/CVPR52734.2025.00496"},{"key":"34_CR88","doi-asserted-by":"crossref","unstructured":"Wang, R., et al.: MoGe-2: accurate monocular geometry with metric scale and sharp details. arXiv preprint: arXiv:2507.02546 (2025)","DOI":"10.52202\/085713-1207"},{"key":"34_CR89","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":"34_CR90","doi-asserted-by":"crossref","unstructured":"Wang, Y., He, X., Peng, S., Tan, D., Zhou, X.: Efficient LoFTR: semi-dense local feature matching with sparse-like speed. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.02047"},{"key":"34_CR91","unstructured":"Wang, Y., et al.: $$\\pi ^3$$: permutation-equivariant visual geometry learning. In: ICLR (2026)"},{"key":"34_CR92","doi-asserted-by":"crossref","unstructured":"Wang, Y., et al.: Adaptive patch deformation for textureless-resilient multi-view stereo. In: CVPR, pp. 1621\u20131630 (2023)","DOI":"10.1109\/CVPR52729.2023.00162"},{"key":"34_CR93","doi-asserted-by":"crossref","unstructured":"Xia, H., Fu, Y., Liu, S., Wang, X.: RGBD objects in the wild: scaling real-world 3D object learning from RGB-D videos. In: CVPR, pp. 22378\u201322389 (2024)","DOI":"10.1109\/CVPR52733.2024.02112"},{"key":"34_CR94","doi-asserted-by":"crossref","unstructured":"Yan, Z., Li, X., Wang, K., Zhang, Z., Li, J., Yang, J.: Multi-modal masked pre-training for monocular panoramic depth completion. In: ECCV, pp. 378\u2013395 (2022)","DOI":"10.1007\/978-3-031-19769-7_22"},{"key":"34_CR95","doi-asserted-by":"crossref","unstructured":"Yang, J., et al.: Fast3R: towards 3D reconstruction of 1000+ images in one forward pass. In: CVPR, pp. 21924\u201321935 (2025)","DOI":"10.1109\/CVPR52734.2025.02042"},{"key":"34_CR96","doi-asserted-by":"crossref","unstructured":"Yang, L., Kang, B., Huang, Z., Xu, X., Feng, J., Zhao, H.: Depth anything: unleashing the power of large-scale unlabeled data. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.00987"},{"key":"34_CR97","doi-asserted-by":"crossref","unstructured":"Yang, L., et al.: Depth anything V2. In: NeurIPS, pp. 21875\u201321911 (2024)","DOI":"10.52202\/079017-0688"},{"key":"34_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":"34_CR99","doi-asserted-by":"crossref","unstructured":"Yao, Y., et al.: BlendedMVS: a large-scale dataset for generalized multi-view stereo networks. In: CVPR, pp. 1790\u20131799 (2020)","DOI":"10.1109\/CVPR42600.2020.00186"},{"key":"34_CR100","doi-asserted-by":"crossref","unstructured":"Zhang, S., et al.: FLARE: feed-forward geometry, appearance and camera estimation from uncalibrated sparse views. In: CVPR, pp. 21936\u201321947 (2025)","DOI":"10.1109\/CVPR52734.2025.02043"},{"key":"34_CR101","doi-asserted-by":"crossref","unstructured":"Zhao, Q., Lin, A., Tan, J., Zhang, J.Y., Ramanan, D., Tulsiani, S.: DiffusionSfM: predicting structure and motion via ray origin and endpoint diffusion. In: CVPR (2025)","DOI":"10.1109\/CVPR52734.2025.00592"},{"key":"34_CR102","doi-asserted-by":"crossref","unstructured":"Zhao, X., Wu, X., Miao, J., Chen, W., Chen, P.C., Li, Z.: ALIKE: accurate and lightweight keypoint detection and descriptor extraction. In: TMM, pp. 3101\u20133112 (2022)","DOI":"10.1109\/TMM.2022.3155927"},{"key":"34_CR103","doi-asserted-by":"crossref","unstructured":"Zheng, J., Zhang, J., Li, J., Tang, R., Gao, S., Zhou, Z.: Structured3D: a large photo-realistic dataset for structured 3D modeling. In: ECCV, pp. 519\u2013535 (2020)","DOI":"10.1007\/978-3-030-58545-7_30"},{"key":"34_CR104","unstructured":"Zheng, X., et al.: PANORAMA: the rise of omnidirectional vision in the embodied AI era. arXiv preprint: arXiv:2509.12989 (2025)"},{"key":"34_CR105","doi-asserted-by":"crossref","unstructured":"Zheng, Y., Harley, A.W., Shen, B., Wetzstein, G., Guibas, L.J.: PointOdyssey: a large-scale synthetic dataset for long-term point tracking. In: ICCV, pp. 19855\u201319865 (2023)","DOI":"10.1109\/ICCV51070.2023.01818"},{"key":"34_CR106","doi-asserted-by":"crossref","unstructured":"Zhong, D., et al.: OmniSAM: omnidirectional segment anything model for UDA in panoramic semantic segmentation. In: ICCV, pp. 23892\u201323901 (2025)","DOI":"10.1109\/ICCV51701.2025.02215"},{"key":"34_CR107","unstructured":"Zhuo, D., Zheng, W., Guo, J., Wu, Y., Zhou, J., Lu, J.: Streaming 4D visual geometry transformer. arXiv preprint: arXiv:2507.11539 (2025)"}],"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\/978-3-032-37369-4_34","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T05:46:26Z","timestamp":1788932786000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37369-4_34"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032373687","9783032373694"],"references-count":107,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37369-4_34","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"}}]}}