{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T05:10:12Z","timestamp":1780463412387,"version":"3.54.1"},"reference-count":52,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T00:00:00Z","timestamp":1683244800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T00:00:00Z","timestamp":1683244800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100012165","name":"Key Technologies Research and Development Program","doi-asserted-by":"publisher","award":["2018AAA0100400"],"award-info":[{"award-number":["2018AAA0100400"]}],"id":[{"id":"10.13039\/501100012165","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Natural Science Foundation of China","doi-asserted-by":"crossref","award":["61922046"],"award-info":[{"award-number":["61922046"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62132012"],"award-info":[{"award-number":["62132012"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Vis Comput"],"published-print":{"date-parts":[[2024,3]]},"DOI":"10.1007\/s00371-023-02863-5","type":"journal-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:01:37Z","timestamp":1683306097000},"page":"1485-1497","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["RDNeRF: relative depth guided NeRF for dense free view synthesis"],"prefix":"10.1007","volume":"40","author":[{"given":"Jiaxiong","family":"Qiu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yifan","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peng-Tao","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ming-Ming","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8179-9122","authenticated-orcid":false,"given":"Bo","family":"Ren","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,5,5]]},"reference":[{"key":"2863_CR1","unstructured":"Aliev, KA., Ulyanov, D., Lempitsky, V.: Neural point-based graphics 2(3):4 (2019). arXiv preprint arXiv:1906.08240"},{"key":"2863_CR2","doi-asserted-by":"crossref","unstructured":"Andraghetti, L., Myriokefalitakis, P., Dovesi, P.L., et\u00a0al.: Enhancing self-supervised monocular depth estimation with traditional visual odometry. In: 2019 International Conference on 3D Vision (3DV), pp. 424\u2013433. IEEE (2019)","DOI":"10.1109\/3DV.2019.00054"},{"key":"2863_CR3","doi-asserted-by":"crossref","unstructured":"Battiato, S., Curti, S., La\u00a0Cascia, M., et\u00a0al.: Depth map generation by image classification. In: Three-Dimensional Image Capture and Applications VI, International Society for Optics and Photonics, pp. 95\u2013104 (2004)","DOI":"10.1117\/12.526634"},{"issue":"6","key":"2863_CR4","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1109\/MSP.2007.905702","volume":"24","author":"S Chan","year":"2007","unstructured":"Chan, S., Shum, H.Y., Ng, K.T.: Image-based rendering and synthesis. IEEE Signal Process. Mag. 24(6), 22\u201333 (2007)","journal-title":"IEEE Signal Process. Mag."},{"key":"2863_CR5","doi-asserted-by":"crossref","unstructured":"Chen, D., Sang, X., Wang, P., et al.: Dense-view synthesis for three-dimensional light-field display based on unsupervised learning. Opt. Express 27(17), 24,624\u201324,641 (2019)","DOI":"10.1364\/OE.27.024624"},{"key":"2863_CR6","unstructured":"Chen, W., Fu, Z., Yang, D., et\u00a0al.: Single-image depth perception in the wild. arXiv preprint arXiv:1604.03901 (2016)"},{"key":"2863_CR7","unstructured":"Chen, Z., Wang, C., Guo, Y.C, et\u00a0al.: Structnerf: Neural radiance fields for indoor scenes with structural hints. arXiv preprint arXiv:2209.05277 (2022)"},{"key":"2863_CR8","doi-asserted-by":"crossref","unstructured":"Dai, A., Chang, A.X., Savva, M., et\u00a0al.: 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":"2863_CR9","doi-asserted-by":"crossref","unstructured":"Dai, P., Zhang, Y., Li, Z., et\u00a0al.: Neural point cloud rendering via multi-plane projection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7830\u20137839 (2020)","DOI":"10.1109\/CVPR42600.2020.00785"},{"key":"2863_CR10","doi-asserted-by":"crossref","unstructured":"Deng, K., Liu, A., Zhu, J.Y., et\u00a0al.: Depth-supervised nerf: Fewer views and faster training for free. arXiv preprint arXiv:2107.02791 (2021)","DOI":"10.1109\/CVPR52688.2022.01254"},{"key":"2863_CR11","doi-asserted-by":"crossref","unstructured":"DeVries, T., Bautista, M.A., Srivastava, N., et\u00a0al .: Unconstrained scene generation with locally conditioned radiance fields. arXiv preprint arXiv:2104.00670 (2021)","DOI":"10.1109\/ICCV48922.2021.01404"},{"key":"2863_CR12","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., et\u00a0al .: An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"2863_CR13","doi-asserted-by":"crossref","unstructured":"Eigen, D., Fergus, R .: Predicting depth, surface normals and semantic labels with a common multi-scale convolutional architecture. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2650\u20132658 (2015)","DOI":"10.1109\/ICCV.2015.304"},{"key":"2863_CR14","doi-asserted-by":"crossref","unstructured":"Flynn, J., Broxton, M., Debevec, P., et\u00a0al.: Deepview: View synthesis with learned gradient descent. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2367\u20132376 (2019)","DOI":"10.1109\/CVPR.2019.00247"},{"key":"2863_CR15","doi-asserted-by":"crossref","unstructured":"Fu, H., Gong, M., Wang, C., et\u00a0al .: Deep ordinal regression network for monocular depth estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2002\u20132011 (2018)","DOI":"10.1109\/CVPR.2018.00214"},{"key":"2863_CR16","doi-asserted-by":"crossref","unstructured":"Glocker, B., Izadi, S., Shotton, J., et\u00a0al.: Real-time RGB-D camera relocalization. In: 2013 IEEE International Symposium on Mixed and Augmented Reality (ISMAR), pp. 173\u2013179. IEEE (2013)","DOI":"10.1109\/ISMAR.2013.6671777"},{"key":"2863_CR17","doi-asserted-by":"crossref","unstructured":"Godard, C., Mac\u00a0Aodha, O., Brostow, G.J.: Unsupervised monocular depth estimation with left-right consistency. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 270\u2013279 (2017)","DOI":"10.1109\/CVPR.2017.699"},{"key":"2863_CR18","doi-asserted-by":"crossref","unstructured":"Gordon, A., Li, H., Jonschkowski, R., et\u00a0al.: Depth from videos in the wild: Unsupervised monocular depth learning from unknown cameras. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 8977\u20138986 (2019)","DOI":"10.1109\/ICCV.2019.00907"},{"issue":"6","key":"2863_CR19","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3272127.3275084","volume":"37","author":"P Hedman","year":"2018","unstructured":"Hedman, P., Philip, J., Price, T., et al.: Deep blending for free-viewpoint image-based rendering. ACM Trans. Graph. (TOG) 37(6), 1\u201315 (2018)","journal-title":"ACM Trans. Graph. (TOG)"},{"issue":"3","key":"2863_CR20","doi-asserted-by":"publisher","first-page":"165","DOI":"10.1145\/964965.808594","volume":"18","author":"JT Kajiya","year":"1984","unstructured":"Kajiya, J.T., Von Herzen, B.P.: Ray tracing volume densities. ACM SIGGRAPH Comput. Graph. 18(3), 165\u2013174 (1984)","journal-title":"ACM SIGGRAPH Comput. Graph."},{"key":"2863_CR21","doi-asserted-by":"crossref","unstructured":"Laina, I., Rupprecht, C., Belagiannis, V., et\u00a0al.: Deeper depth prediction with fully convolutional residual networks. In: 2016 Fourth International Conference on 3D Vision (3DV), pp. 239\u2013248. IEEE (2016)","DOI":"10.1109\/3DV.2016.32"},{"key":"2863_CR22","doi-asserted-by":"crossref","unstructured":"Lindell, D.B., Martel, J.N., Wetzstein, G.: Autoint: Automatic integration for fast neural volume rendering. arXiv preprint arXiv:2012.01714 (2020)","DOI":"10.1109\/CVPR46437.2021.01432"},{"issue":"10","key":"2863_CR23","doi-asserted-by":"publisher","first-page":"2024","DOI":"10.1109\/TPAMI.2015.2505283","volume":"38","author":"F Liu","year":"2015","unstructured":"Liu, F., Shen, C., Lin, G., et al.: Learning depth from single monocular images using deep convolutional neural fields. IEEE Trans. Pattern Anal. Mach. Intell. 38(10), 2024\u20132039 (2015)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2863_CR24","unstructured":"Liu, L., Gu, J., Lin, K.Z., et\u00a0al.: Neural sparse voxel fields. arXiv preprint arXiv:2007.11571 (2020)"},{"key":"2863_CR25","doi-asserted-by":"crossref","unstructured":"Martin-Brualla, R., Radwan, N., Sajjadi, M.S., et\u00a0al .: Nerf in the wild: Neural radiance fields for unconstrained photo collections. arXiv preprint arXiv:2008.02268 (2020)","DOI":"10.1109\/CVPR46437.2021.00713"},{"issue":"2","key":"2863_CR26","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1109\/2945.468400","volume":"1","author":"N Max","year":"1995","unstructured":"Max, N.: Optical models for direct volume rendering. IEEE Trans. Visual Comput. Graph. 1(2), 99\u2013108 (1995)","journal-title":"IEEE Trans. Visual Comput. Graph."},{"key":"2863_CR27","doi-asserted-by":"crossref","unstructured":"Mildenhall, B., Srinivasan, P.P., Tancik, M., et\u00a0al.: Nerf: Representing scenes as neural radiance fields for view synthesis. In: European Conference on Computer Vision, pp. 405\u2013421. Springer (2020)","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"2863_CR28","doi-asserted-by":"crossref","unstructured":"Neff, T., Stadlbauer, P., Parger, M., et\u00a0al.: Donerf: Towards real-time rendering of compact neural radiance fields using depth oracle networks. In: Computer Graphics Forum, Wiley Online Library, pp. 45\u201359 (2021)","DOI":"10.1111\/cgf.14340"},{"issue":"4","key":"2863_CR29","doi-asserted-by":"publisher","first-page":"703","DOI":"10.1109\/TIP.2009.2012884","volume":"18","author":"HT Nguyen","year":"2009","unstructured":"Nguyen, H.T., Do, M.N.: Error analysis for image-based rendering with depth information. IEEE Trans. Image Process. 18(4), 703\u2013716 (2009)","journal-title":"IEEE Trans. Image Process."},{"issue":"6","key":"2863_CR30","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3130800.3130855","volume":"36","author":"E Penner","year":"2017","unstructured":"Penner, E., Zhang, L.: Soft 3d reconstruction for view synthesis. ACM Trans. Graph. (TOG) 36(6), 1\u201311 (2017)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"2863_CR31","doi-asserted-by":"crossref","unstructured":"Pumarola, A., Corona, E., Pons-Moll, G., et\u00a0al.: D-nerf: Neural radiance fields for dynamic scenes. arXiv preprint arXiv:2011.13961 (2020)","DOI":"10.1109\/CVPR46437.2021.01018"},{"key":"2863_CR32","doi-asserted-by":"crossref","unstructured":"Qi, X., Liao, R., Liu, Z., et\u00a0al.: Geonet: Geometric neural network for joint depth and surface normal estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 283\u2013291 (2018)","DOI":"10.1109\/CVPR.2018.00037"},{"key":"2863_CR33","unstructured":"Ranftl, R., Lasinger, K., Hafner, D., et\u00a0al.: Towards robust monocular depth estimation: Mixing datasets for zero-shot cross-dataset transfer. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) (2020)"},{"key":"2863_CR34","doi-asserted-by":"crossref","unstructured":"Reizenstein, J., Shapovalov, R., Henzler, P., et\u00a0al.: Common objects in 3D: Large-scale learning and evaluation of real-life 3D category reconstruction. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10,901\u201310,911 (2021)","DOI":"10.1109\/ICCV48922.2021.01072"},{"key":"2863_CR35","doi-asserted-by":"crossref","unstructured":"Riegler, G., Koltun, V.: Free view synthesis. In: European Conference on Computer Vision (2020)","DOI":"10.1109\/CVPR46437.2021.01204"},{"key":"2863_CR36","doi-asserted-by":"crossref","unstructured":"Riegler, G., Koltun, V.: Stable view synthesis. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2021)","DOI":"10.1109\/CVPR46437.2021.01204"},{"key":"2863_CR37","doi-asserted-by":"crossref","unstructured":"Roessle, B., Barron, J.T., Mildenhall, B., et\u00a0al.: Dense depth priors for neural radiance fields from sparse input views. arXiv preprint arXiv:2112.03288 (2021)","DOI":"10.1109\/CVPR52688.2022.01255"},{"key":"2863_CR38","doi-asserted-by":"crossref","unstructured":"Schonberger, J.L., Frahm, J.M .: Structure-from-motion revisited. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4104\u20134113 (2016)","DOI":"10.1109\/CVPR.2016.445"},{"key":"2863_CR39","doi-asserted-by":"crossref","unstructured":"Srinivasan, P.P., Tucker, R., Barron , J.T., et\u00a0al.: Pushing the boundaries of view extrapolation with multiplane images. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 175\u2013184 (2019)","DOI":"10.1109\/CVPR.2019.00026"},{"key":"2863_CR40","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., et\u00a0al.: Attention is all you need. arXiv preprint arXiv:1706.03762 (2017)"},{"key":"2863_CR41","doi-asserted-by":"crossref","unstructured":"Wang, C., Lucey, S., Perazzi, F., et\u00a0al.: Web stereo video supervision for depth prediction from dynamic scenes. In: 2019 International Conference on 3D Vision (3DV), pp. 348\u2013357. IEEE (2019)","DOI":"10.1109\/3DV.2019.00046"},{"key":"2863_CR42","unstructured":"Wang, P., Chen, X., Chen, T., et\u00a0al.: Is attention all nerf needs? arXiv preprint arXiv:2207.13298 (2022)"},{"issue":"4","key":"2863_CR43","doi-asserted-by":"publisher","first-page":"600","DOI":"10.1109\/TIP.2003.819861","volume":"13","author":"Z Wang","year":"2004","unstructured":"Wang, Z., Bovik, A.C., Sheikh, H.R., et al.: Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13(4), 600\u2013612 (2004)","journal-title":"IEEE Trans. Image Process."},{"key":"2863_CR44","doi-asserted-by":"crossref","unstructured":"Wei, Y., Liu, S., Rao, Y., et\u00a0al.: Nerfingmvs: Guided optimization of neural radiance fields for indoor multi-view stereo. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5610\u20135619 (2021)","DOI":"10.1109\/ICCV48922.2021.00556"},{"issue":"4","key":"2863_CR45","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3528223.3530085","volume":"41","author":"X Wu","year":"2022","unstructured":"Wu, X., Xu, J., Zhu, Z., et al.: Scalable neural indoor scene rendering. ACM Trans. Graph. (TOG) 41(4), 1\u201316 (2022)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"2863_CR46","doi-asserted-by":"crossref","unstructured":"Yin, W., Zhang, J., Wang, O., et\u00a0al.: Learning to recover 3d scene shape from a single image. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 204\u2013213 (2021)","DOI":"10.1109\/CVPR46437.2021.00027"},{"key":"2863_CR47","doi-asserted-by":"crossref","unstructured":"Yu, A., Ye, V., Tancik, M., et\u00a0al.: pixelnerf: Neural radiance fields from one or few images. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4578\u20134587 (2021)","DOI":"10.1109\/CVPR46437.2021.00455"},{"issue":"1","key":"2863_CR48","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.image.2003.07.001","volume":"19","author":"C Zhang","year":"2004","unstructured":"Zhang, C., Chen, T.: A survey on image-based rendering-representation, sampling and compression. Signal Process. Image Commun. 19(1), 1\u201328 (2004)","journal-title":"Signal Process. Image Commun."},{"key":"2863_CR49","unstructured":"Zhang, K., Riegler, G., Snavely, N., et\u00a0al.: Nerf++: Analyzing and improving neural radiance fields. arXiv preprint arXiv:2010.07492 (2020)"},{"key":"2863_CR50","doi-asserted-by":"crossref","unstructured":"Zhang, R., Isola, P., Efros, A.A., et\u00a0al.: The unreasonable effectiveness of deep features as a perceptual metric. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 586\u2013595 (2018)","DOI":"10.1109\/CVPR.2018.00068"},{"key":"2863_CR51","doi-asserted-by":"crossref","unstructured":"Zhou, T., Brown, M., Snavely, N., et\u00a0al.: Unsupervised learning of depth and ego-motion from video. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1851\u20131858 (2017)","DOI":"10.1109\/CVPR.2017.700"},{"key":"2863_CR52","doi-asserted-by":"crossref","unstructured":"Zhou, T., Tucker, R., Flynn, J., et\u00a0al.: Stereo magnification: Learning view synthesis using multiplane images. arXiv preprint arXiv:1805.09817 (2018)","DOI":"10.1145\/3197517.3201323"}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-023-02863-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00371-023-02863-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-023-02863-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,19]],"date-time":"2024-02-19T08:10:48Z","timestamp":1708330248000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00371-023-02863-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,5]]},"references-count":52,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2024,3]]}},"alternative-id":["2863"],"URL":"https:\/\/doi.org\/10.1007\/s00371-023-02863-5","relation":{},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"value":"0178-2789","type":"print"},{"value":"1432-2315","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,5,5]]},"assertion":[{"value":"27 March 2023","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 May 2023","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}