{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,22]],"date-time":"2026-01-22T21:51:43Z","timestamp":1769118703367,"version":"3.49.0"},"reference-count":41,"publisher":"Springer Science and Business Media LLC","issue":"20","license":[{"start":{"date-parts":[[2024,8,6]],"date-time":"2024-08-06T00:00:00Z","timestamp":1722902400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,8,6]],"date-time":"2024-08-06T00:00:00Z","timestamp":1722902400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61902158"],"award-info":[{"award-number":["61902158"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"DOI":"10.1007\/s11042-024-19978-z","type":"journal-article","created":{"date-parts":[[2024,8,6]],"date-time":"2024-08-06T07:02:29Z","timestamp":1722927749000},"page":"22539-22559","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["PIDSNeRF: pose interpolation depth supervision neural radiance fields for view synthesis from challenging input"],"prefix":"10.1007","volume":"84","author":[{"given":"Jianxin","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5360-0788","authenticated-orcid":false,"given":"Haijian","family":"Shao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xing","family":"Deng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yingtao","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,8,6]]},"reference":[{"key":"19978_CR1","doi-asserted-by":"crossref","unstructured":"Yao Y, Luo Z, Li S, Fang T, Quan L (2018) Mvsnet: Depth inference for unstructured multi-view stereo. In: Proceedings of the European conference on computer vision (ECCV), pp 767\u2013783","DOI":"10.1007\/978-3-030-01237-3_47"},{"key":"19978_CR2","doi-asserted-by":"crossref","unstructured":"Wang F, Galliani S, Vogel C, Speciale P, Pollefeys M (2021) Patchmatchnet: Learned multi-view patchmatch stereo. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 14194\u201314203","DOI":"10.1109\/CVPR46437.2021.01397"},{"issue":"1","key":"19978_CR3","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1145\/3503250","volume":"65","author":"B Mildenhall","year":"2021","unstructured":"Mildenhall B, Srinivasan PP, Tancik M, Barron JT, Ramamoorthi R, Ng R (2021) Nerf: Representing scenes as neural radiance fields for view synthesis. Commun ACM 65(1):99\u2013106","journal-title":"Commun ACM"},{"key":"19978_CR4","doi-asserted-by":"crossref","unstructured":"Tancik M, Casser V, Yan X, Pradhan S, Mildenhall B, Srinivasan PP, Barron JT, Kretzschmar H (2022) Block-nerf: Scalable large scene neural view synthesis. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 8248\u20138258","DOI":"10.1109\/CVPR52688.2022.00807"},{"key":"19978_CR5","doi-asserted-by":"crossref","unstructured":"Martin-Brualla R, Radwan N, Sajjadi MS, Barron JT, Dosovitskiy A, Duckworth D (2021) Nerf in the wild: Neural radiance fields for unconstrained photo collections. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 7210\u20137219","DOI":"10.1109\/CVPR46437.2021.00713"},{"key":"19978_CR6","doi-asserted-by":"crossref","unstructured":"Deng K, Liu A, Zhu J-Y, Ramanan D (2022) Depth-supervised nerf: Fewer views and faster training for free. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 12882\u201312891","DOI":"10.1109\/CVPR52688.2022.01254"},{"issue":"4","key":"19978_CR7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3306346.3322980","volume":"38","author":"B Mildenhall","year":"2019","unstructured":"Mildenhall B, Srinivasan PP, Ortiz-Cayon R, Kalantari NK, Ramamoorthi R, Ng R, Kar A (2019) Local light field fusion: Practical view synthesis with prescriptive sampling guidelines. ACM Transactions on Graphics (TOG) 38(4):1\u201314","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"19978_CR8","doi-asserted-by":"crossref","unstructured":"Jensen R, Dahl A, Vogiatzis G, Tola E, Aan\u00e6s H (2014) Large scale multi-view stereopsis evaluation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 406\u2013413","DOI":"10.1109\/CVPR.2014.59"},{"issue":"10","key":"19978_CR9","doi-asserted-by":"publisher","first-page":"6642","DOI":"10.1109\/TCSVT.2022.3177320","volume":"32","author":"L Yan","year":"2022","unstructured":"Yan L, Ma S, Wang Q, Chen Y, Zhang X, Savakis A, Liu D (2022) Video captioning using global-local representation. IEEE Trans Circuits Syst Video Technol 32(10):6642\u20136656","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"issue":"1","key":"19978_CR10","doi-asserted-by":"publisher","first-page":"393","DOI":"10.1109\/TCSVT.2022.3202574","volume":"33","author":"L Yan","year":"2022","unstructured":"Yan L, Wang Q, Ma S, Wang J, Yu C (2022) Solve the puzzle of instance segmentation in videos: A weakly supervised framework with spatio-temporal collaboration. IEEE Trans Circuits Syst Video Technol 33(1):393\u2013406","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"19978_CR11","first-page":"12826","volume":"35","author":"W Wang","year":"2022","unstructured":"Wang W, Liang J, Liu D (2022) Learning equivariant segmentation with instance-unique querying. Adv Neural Inf Process Syst 35:12826\u201312840","journal-title":"Adv Neural Inf Process Syst"},{"key":"19978_CR12","doi-asserted-by":"crossref","unstructured":"Lu Y, Wang Q, Ma S, Geng T, Chen YV, Chen H, Liu D (2023) Transflow: Transformer as flow learner. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 18063\u201318073","DOI":"10.1109\/CVPR52729.2023.01732"},{"key":"19978_CR13","doi-asserted-by":"crossref","unstructured":"Schonberger JL, Frahm J-M (2016) Structure-from-motion revisited. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4104\u20134113","DOI":"10.1109\/CVPR.2016.445"},{"key":"19978_CR14","doi-asserted-by":"crossref","unstructured":"Chang D, Bo\u017ei\u010d A, Zhang T, Yan Q, Chen Y, S\u00fcsstrunk S, Nie\u00dfner M (2022) Rc-mvsnet: unsupervised multi-view stereo with neural rendering. In: European conference on computer vision, Springer, pp 665\u2013680","DOI":"10.1007\/978-3-031-19821-2_38"},{"key":"19978_CR15","doi-asserted-by":"crossref","unstructured":"Maturana D, Scherer S (2015) Voxnet: A 3d convolutional neural network for real-time object recognition. In: 2015 IEEE\/RSJ International conference on intelligent robots and systems (IROS), IEEE, pp 922\u201392","DOI":"10.1109\/IROS.2015.7353481"},{"key":"19978_CR16","unstructured":"Wu Z, Song S, Khosla A, Yu F, Zhang L, Tang X, Xiao J (2015) 3d shapenets: A deep representation for volumetric shapes. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1912\u20131920"},{"key":"19978_CR17","doi-asserted-by":"crossref","unstructured":"H\u00e4ne C, Tulsiani S, Malik J (2017) Hierarchical surface prediction for 3d object reconstruction. In: 2017 International Conference on 3D Vision (3DV), IEEE, pp 412\u2013420","DOI":"10.1109\/3DV.2017.00054"},{"key":"19978_CR18","doi-asserted-by":"crossref","unstructured":"Tatarchenko M, Dosovitskiy A, Brox T (2017) Octree generating networks: Efficient convolutional architectures for high-resolution 3d outputs. In: Proceedings of the IEEE international conference on computer vision, pp 2088\u20132096","DOI":"10.1109\/ICCV.2017.230"},{"key":"19978_CR19","doi-asserted-by":"crossref","unstructured":"Wang N, Zhang Y, Li Z, Fu Y, Liu W, Jiang Y-G (2018) Pixel2mesh: Generating 3d mesh models from single rgb images. In: Proceedings of the European conference on computer vision (ECCV), pp 52\u201367","DOI":"10.1007\/978-3-030-01252-6_4"},{"key":"19978_CR20","doi-asserted-by":"crossref","unstructured":"Kato H, Ushiku Y, Harada T (2018) Neural 3d mesh renderer. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3907\u20133916","DOI":"10.1109\/CVPR.2018.00411"},{"key":"19978_CR21","doi-asserted-by":"crossref","unstructured":"Levy D, Peleg A, Pearl N, Rosenbaum D, Akkaynak D, Korman S, Treibitz T (2023) Seathru-nerf: Neural radiance fields in scattering media. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 56\u201365","DOI":"10.1109\/CVPR52729.2023.00014"},{"key":"19978_CR22","unstructured":"Wang Z, Li L, Shen Z, Shen L, Bo L (2022) 4k-nerf: High fidelity neural radiance fields at ultra high resolutions. arXiv preprint arXiv:2212.04701"},{"key":"19978_CR23","doi-asserted-by":"crossref","unstructured":"Barron JT, Mildenhall B, Tancik M, Hedman P, Martin-Brualla R, Srinivasan PP (2021) Mip-nerf: A multiscale representation for anti-aliasing neural radiance fields. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 5855\u20135864","DOI":"10.1109\/ICCV48922.2021.00580"},{"key":"19978_CR24","doi-asserted-by":"crossref","unstructured":"Xu Q, Xu Z, Philip J, Bi S, Shu Z, Sunkavalli K, Neumann U (2022) Point-nerf: Point-based neural radiance fields. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 5438\u20135448","DOI":"10.1109\/CVPR52688.2022.00536"},{"key":"19978_CR25","doi-asserted-by":"crossref","unstructured":"Xu Q, Xu Z, Philip J, Bi S, Shu Z, Sunkavalli K, Neumann U (2022) Point-nerf: Point-based neural radiance fields. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 5438\u20135448","DOI":"10.1109\/CVPR52688.2022.00536"},{"key":"19978_CR26","doi-asserted-by":"crossref","unstructured":"Fridovich-Keil S, Yu A, Tancik M, Chen Q, Recht B, Kanazawa A (2022) Plenoxels: Radiance fields without neural networks. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 5501\u20135510","DOI":"10.1109\/CVPR52688.2022.00542"},{"key":"19978_CR27","first-page":"15651","volume":"33","author":"L Liu","year":"2020","unstructured":"Liu L, Gu J, Zaw Lin K, Chua T-S, Theobalt C (2020) Neural sparse voxel fields. Adv Neural Inf Process Syst 33:15651\u201315663","journal-title":"Adv Neural Inf Process Syst"},{"key":"19978_CR28","doi-asserted-by":"crossref","unstructured":"Sun C, Sun M, Chen H-T (2022) Direct voxel grid optimization: Super-fast convergence for radiance fields reconstruction. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 5459\u20135469","DOI":"10.1109\/CVPR52688.2022.00538"},{"issue":"4","key":"19978_CR29","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3528223.3530127","volume":"41","author":"T M\u00fcller","year":"2022","unstructured":"M\u00fcller T, Evans A, Schied C, Keller A (2022) Instant neural graphics primitives with a multiresolution hash encoding. ACM Transactions on Graphics (ToG) 41(4):1\u201315","journal-title":"ACM Transactions on Graphics (ToG)"},{"key":"19978_CR30","doi-asserted-by":"crossref","unstructured":"Yu A, Ye V, Tancik M, Kanazawa A (2021) 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","DOI":"10.1109\/CVPR46437.2021.00455"},{"key":"19978_CR31","doi-asserted-by":"crossref","unstructured":"Chen A, Xu Z, Zhao F, Zhang X, Xiang F, Yu, J, Su H (2021) Mvsnerf: Fast generalizable radiance field reconstruction from multi-view stereo. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 14124\u201314133","DOI":"10.1109\/ICCV48922.2021.01386"},{"key":"19978_CR32","doi-asserted-by":"crossref","unstructured":"Niemeyer M, Barron JT, Mildenhall B, Sajjadi MS, Geiger A, Radwan N (2022) Regnerf: Regularizing neural radiance fields for view synthesis from sparse inputs. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 5480\u20135490","DOI":"10.1109\/CVPR52688.2022.00540"},{"key":"19978_CR33","doi-asserted-by":"crossref","unstructured":"Yang J, Pavone M, Wang Y (2023) Freenerf: Improving few-shot neural rendering with free frequency regularization. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 8254\u20138263","DOI":"10.1109\/CVPR52729.2023.00798"},{"key":"19978_CR34","doi-asserted-by":"crossref","unstructured":"Mildenhall B, Hedman P, Martin-Brualla R, Srinivasan PP, Barron JT (2022) Nerf in the dark: High dynamic range view synthesis from noisy raw images. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 16190\u201316199","DOI":"10.1109\/CVPR52688.2022.01571"},{"key":"19978_CR35","doi-asserted-by":"crossref","unstructured":"Ling L, Sheng Y, Tu Z, Zhao W, Xin C, Wan K, Yu L, Guo Q, Yu Z, Lu Y et al (2023) Dl3dv-10k: A large-scale scene dataset for deep learning-based 3d vision. arXiv preprint arXiv:2312.16256","DOI":"10.1109\/CVPR52733.2024.02092"},{"issue":"4","key":"19978_CR36","doi-asserted-by":"publisher","first-page":"600","DOI":"10.1109\/TIP.2003.819861","volume":"13","author":"Z Wang","year":"2004","unstructured":"Wang Z, Bovik AC, Sheikh HR, Simoncelli EP (2004) Image quality assessment: from error visibility to structural similarity. IEEE Trans Image Process 13(4):600\u2013612","journal-title":"IEEE Trans Image Process"},{"key":"19978_CR37","doi-asserted-by":"crossref","unstructured":"Zhang R, Isola P, Efros AA, Shechtman E, Wang O (2018) 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","DOI":"10.1109\/CVPR.2018.00068"},{"key":"19978_CR38","doi-asserted-by":"crossref","unstructured":"Chibane J, Bansal A, Lazova V, Pons-Moll G (2021) Stereo radiance fields (srf): Learning view synthesis for sparse views of novel scenes. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 7911\u20137920","DOI":"10.1109\/CVPR46437.2021.00782"},{"key":"19978_CR39","doi-asserted-by":"crossref","unstructured":"Jain A, Tancik M, Abbeel P (2021) Putting nerf on a diet: Semantically consistent few-shot view synthesis. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 5885\u20135894","DOI":"10.1109\/ICCV48922.2021.00583"},{"key":"19978_CR40","first-page":"25018","volume":"35","author":"Z Yu","year":"2022","unstructured":"Yu Z, Peng S, Niemeyer M, Sattler T, Geiger A (2022) Monosdf: Exploring monocular geometric cues for neural implicit surface reconstruction. Adv Neural Inf Process Syst 35:25018\u201325032","journal-title":"Adv Neural Inf Process Syst"},{"key":"19978_CR41","doi-asserted-by":"crossref","unstructured":"Wang G, Chen Z, Loy CC, Liu Z (2023) Sparsenerf: Distilling depth ranking for few-shot novel view synthesis. arXiv preprint arXiv:2303.16196","DOI":"10.1109\/ICCV51070.2023.00832"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-024-19978-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-024-19978-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-024-19978-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,2]],"date-time":"2025-07-02T11:22:22Z","timestamp":1751455342000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-024-19978-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,6]]},"references-count":41,"journal-issue":{"issue":"20","published-online":{"date-parts":[[2025,6]]}},"alternative-id":["19978"],"URL":"https:\/\/doi.org\/10.1007\/s11042-024-19978-z","relation":{},"ISSN":["1573-7721"],"issn-type":[{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,8,6]]},"assertion":[{"value":"15 April 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 June 2024","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 July 2024","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 August 2024","order":4,"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 they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflicts of interest"}}]}}