{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T07:26:24Z","timestamp":1740122784340,"version":"3.37.3"},"reference-count":29,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2024,7,22]],"date-time":"2024-07-22T00:00:00Z","timestamp":1721606400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,7,22]],"date-time":"2024-07-22T00:00:00Z","timestamp":1721606400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100014188","name":"Ministry of Science and ICT, South Korea","doi-asserted-by":"publisher","award":["2022R1F1A1074546","NRF-2022R1C1C1011084","NRF-2022R1C1C1011084","2022R1F1A1074546"],"award-info":[{"award-number":["2022R1F1A1074546","NRF-2022R1C1C1011084","NRF-2022R1C1C1011084","2022R1F1A1074546"]}],"id":[{"id":"10.13039\/501100014188","id-type":"DOI","asserted-by":"publisher"}]},{"name":"BK21 FOUR Project"},{"DOI":"10.13039\/501100010446","name":"Institute for Basic Science","doi-asserted-by":"publisher","award":["R015-D1"],"award-info":[{"award-number":["R015-D1"]}],"id":[{"id":"10.13039\/501100010446","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003052","name":"Ministry of Trade, Industry and Energy","doi-asserted-by":"publisher","award":["P0022098"],"award-info":[{"award-number":["P0022098"]}],"id":[{"id":"10.13039\/501100003052","id-type":"DOI","asserted-by":"publisher"}]},{"name":"SKKU-SMC and SKKU-KBSMC Future Convergence Research Program"},{"name":"SKKU seed"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Process Lett"],"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Neural radiance field (NeRF) is an emerging view synthesis method that samples points in a three-dimensional (3D) space and estimates their existence and color probabilities. The disadvantage of NeRF is that it requires a long training time since it samples many 3D points. In addition, if one samples points from occluded regions or in the space where an object is unlikely to exist, the rendering quality of NeRF can be degraded. These issues can be solved by estimating the geometry of 3D scene. This paper proposes a near-surface sampling framework to improve the rendering quality of NeRF. To this end, the proposed method estimates the surface of a 3D object using depth images of the training set and performs sampling only near the estimated surface. To obtain depth information on a novel view, the paper proposes a 3D point cloud generation method and a simple refining method for projected depth from a point cloud. Experimental results show that the proposed near-surface sampling NeRF framework can significantly improve the rendering quality, compared to the original NeRF and three different state-of-the-art NeRF methods. In addition, one can significantly accelerate the training time of a NeRF model with the proposed near-surface sampling framework.<\/jats:p>","DOI":"10.1007\/s11063-024-11654-5","type":"journal-article","created":{"date-parts":[[2024,7,22]],"date-time":"2024-07-22T04:01:39Z","timestamp":1721620899000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Improving Neural Radiance Fields Using Near-Surface Sampling with Point Cloud Generation"],"prefix":"10.1007","volume":"56","author":[{"given":"Hye Bin","family":"Yoo","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hyun Min","family":"Han","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sung Soo","family":"Hwang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4226-3760","authenticated-orcid":false,"given":"Il Yong","family":"Chun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,7,22]]},"reference":[{"key":"11654_CR1","volume-title":"3D Computer graphics","author":"W Alan","year":"1993","unstructured":"Alan W (1993) 3D Computer graphics. Addison-Wesley, Boston"},{"key":"11654_CR2","doi-asserted-by":"publisher","unstructured":"Boss M, Braun R, Jampani V, et\u00a0al (2021) NeRD: neural reflectance decomposition from image collections. In: IEEE\/CVF international conference on computer vision, pp 12664\u201312674. https:\/\/doi.org\/10.1109\/ICCV48922.2021.01245","DOI":"10.1109\/ICCV48922.2021.01245"},{"key":"11654_CR3","unstructured":"Cernea D (2020) OpenMVS: multi-view stereo reconstruction library. https:\/\/cdcseacave.github.io\/openMVS"},{"key":"11654_CR4","doi-asserted-by":"publisher","unstructured":"Chen SE, Williams L (1993) View interpolation for image synthesis. In: Proceedings of the conference on computer graphics and interactive techniques, pp 279\u2013288. https:\/\/doi.org\/10.1145\/166117.166153","DOI":"10.1145\/166117.166153"},{"key":"11654_CR5","doi-asserted-by":"publisher","unstructured":"Deng K, Liu A, Zhu JY, et\u00a0al (2022) Depth-supervised NeRF: fewer views and faster training for free. In: IEEE\/CVF conference on computer vision and pattern recognition, pp 12872\u201312881. https:\/\/doi.org\/10.1109\/CVPR52688.2022.01254","DOI":"10.1109\/CVPR52688.2022.01254"},{"key":"11654_CR6","doi-asserted-by":"publisher","unstructured":"Draelos M, Qiu Q, Bronstein A, et\u00a0al (2015) Intel realsense = real low cost gaze. In: IEEE international conference on image processing, pp 2520\u20132524. https:\/\/doi.org\/10.1109\/ICIP.2015.7351256","DOI":"10.1109\/ICIP.2015.7351256"},{"key":"11654_CR7","doi-asserted-by":"publisher","unstructured":"Gortler SJ, Grzeszczuk R, Szeliski R, et\u00a0al (1996) The lumigraph. In: Proceedings of the conference on computer graphics and interactive techniques, pp 43\u201354. https:\/\/doi.org\/10.1145\/237170.237200","DOI":"10.1145\/237170.237200"},{"key":"11654_CR8","volume-title":"Multiple view geometry in computer vision","author":"R Hartley","year":"2003","unstructured":"Hartley R, Zisserman A (2003) Multiple view geometry in computer vision, 2nd edn. Cambridge University Press, Cambridge","edition":"2"},{"key":"11654_CR9","doi-asserted-by":"publisher","unstructured":"Hu T, Liu S, Chen Y, et\u00a0al (2022) EfficientNeRF efficient neural radiance fields. In: IEEE\/CVF conference on computer vision and pattern recognition, pp 12902\u201312911. https:\/\/doi.org\/10.1109\/CVPR52688.2022.01256","DOI":"10.1109\/CVPR52688.2022.01256"},{"key":"11654_CR10","doi-asserted-by":"publisher","unstructured":"Johari MM, Lepoittevin Y, Fleuret F (2022) GeoNeRF: generalizing nerf with geometry priors. In: IEEE\/CVF conference on computer vision and pattern recognition, pp 18344\u201318347. https:\/\/doi.org\/10.1109\/CVPR52688.2022.01782","DOI":"10.1109\/CVPR52688.2022.01782"},{"key":"11654_CR11","doi-asserted-by":"publisher","unstructured":"Levoy M, Hanrahan P (1996) Light field rendering. In: Proceedings of the conference on computer graphics and interactive techniques, pp 31\u201342. https:\/\/doi.org\/10.1145\/237170.237199","DOI":"10.1145\/237170.237199"},{"key":"11654_CR12","doi-asserted-by":"publisher","unstructured":"Lin CH, Ma WC, Torralba A, et\u00a0al (2021) BARF: bundle-adjusting neural radiance fields. In: IEEE\/CVF international conference on computer vision, pp 5721\u20135731. https:\/\/doi.org\/10.1109\/ICCV48922.2021.00569","DOI":"10.1109\/ICCV48922.2021.00569"},{"key":"11654_CR13","doi-asserted-by":"publisher","unstructured":"Lindell DB, Martel JNP, Wetzstein G (2021) AutoInt: automatic integration for fast neural volume rendering. In: IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 14551\u201314560. https:\/\/doi.org\/10.1109\/CVPR46437.2021.01432","DOI":"10.1109\/CVPR46437.2021.01432"},{"key":"11654_CR14","unstructured":"Liu L, Gu J, Lin KZ, et\u00a0al (2020) Neural sparse voxel fields. In: Proceedings of the international conference on neural information processing systems, pp 15651\u201315663"},{"key":"11654_CR15","doi-asserted-by":"publisher","first-page":"926","DOI":"10.1002\/esp.3332","volume":"38","author":"K Mankoff","year":"2013","unstructured":"Mankoff K, Russo T (2013) The Kinect: a low-cost, high-resolution, short-range 3d camera. Earth Surf Proc Land 38:926\u2013936. https:\/\/doi.org\/10.1002\/esp.3332","journal-title":"Earth Surf Proc Land"},{"key":"11654_CR16","doi-asserted-by":"publisher","unstructured":"Martin-Brualla R, Radwan N, Sajjadi MSM, et\u00a0al (2021) NeRF in the wild: neural radiance fields for unconstrained photo collections. In: IEEE\/CVF conference on computer vision and pattern recognition, pp 7206\u20137215. https:\/\/doi.org\/10.1109\/CVPR46437.2021.00713","DOI":"10.1109\/CVPR46437.2021.00713"},{"key":"11654_CR17","doi-asserted-by":"publisher","unstructured":"Mildenhall B, Srinivasan PP, Tancik M, et\u00a0al (2020) NeRF: Representing scenes as neural radiance fields for view synthesis. In: Proceedings of the European conference on computer vision, pp 405\u2013421. https:\/\/doi.org\/10.1007\/978-3-030-58452-8_24","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"11654_CR18","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 et al (2022) Instant neural graphics primitives with a multiresolution hash encoding. ACM Trans Graph 41:1\u201315. https:\/\/doi.org\/10.1145\/3528223.3530127","journal-title":"ACM Trans Graph"},{"key":"11654_CR19","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1111\/cgf.14340","volume":"40","author":"T Neff","year":"2021","unstructured":"Neff T, Stadlbauer P, Parger M et al (2021) DONeRF: towards real-time rendering of neural radiance fields using depth oracle networks. Comput Graph Forum 40:45\u201349. https:\/\/doi.org\/10.1111\/cgf.14340","journal-title":"Comput Graph Forum"},{"key":"11654_CR20","doi-asserted-by":"publisher","unstructured":"Niemeyer M, Geiger A (2021) GIRAFFE: representing scenes as compositional generative neural feature fields. In: IEEE\/CVF conference on computer vision and pattern recognition, pp 11448\u201311459. https:\/\/doi.org\/10.1109\/CVPR46437.2021.01129","DOI":"10.1109\/CVPR46437.2021.01129"},{"key":"11654_CR21","doi-asserted-by":"publisher","unstructured":"Park K, Sinha U, Barron JT, et\u00a0al (2021) Nerfies: deformable neural radiance fields. In: IEEE\/CVF international conference on computer vision, pp 5845\u20135854. https:\/\/doi.org\/10.1109\/ICCV48922.2021.00581","DOI":"10.1109\/ICCV48922.2021.00581"},{"key":"11654_CR22","doi-asserted-by":"publisher","unstructured":"Pumarola A, Corona E, Pons-Moll G, et\u00a0al (2021) D-NeRF: neural radiance fields for dynamic scenes. In: IEEE\/CVF conference on computer vision and pattern recognition, pp 10313\u201310322. https:\/\/doi.org\/10.1109\/CVPR46437.2021.01018","DOI":"10.1109\/CVPR46437.2021.01018"},{"key":"11654_CR23","doi-asserted-by":"publisher","unstructured":"Rebain D, Jiang W, Yazdani S, et\u00a0al (2021) DeRF: decomposed radiance fields. In: IEEE\/CVF conference on computer vision and pattern recognition, pp 14148\u201314156. https:\/\/doi.org\/10.1109\/CVPR46437.2021.01393","DOI":"10.1109\/CVPR46437.2021.01393"},{"key":"11654_CR24","doi-asserted-by":"publisher","unstructured":"Shade J, Gortler S, He Lw, et\u00a0al (1998) Layered depth images. In: Proceedings of the conference on computer graphics and interactive techniques, pp 231\u2013242. https:\/\/doi.org\/10.1145\/280814.280882","DOI":"10.1145\/280814.280882"},{"key":"11654_CR25","doi-asserted-by":"publisher","unstructured":"Srinivasan PP, Deng B, Zhang X, et\u00a0al (2021) NeRV: neural reflectance and visibility fields for relighting and view synthesis. In: IEEE\/CVF conference on computer vision and pattern recognition, pp 7491\u20137500, https:\/\/doi.org\/10.1109\/CVPR46437.2021.00741","DOI":"10.1109\/CVPR46437.2021.00741"},{"key":"11654_CR26","doi-asserted-by":"publisher","unstructured":"Xie C, Park K, Martin-Brualla R, et\u00a0al (2021) Fig-NeRF: figure-ground neural radiance fields for 3d object category modelling. In: International conference on 3D vision, pp 962\u2013971. https:\/\/doi.org\/10.1109\/3DV53792.2021.00104","DOI":"10.1109\/3DV53792.2021.00104"},{"key":"11654_CR27","doi-asserted-by":"publisher","unstructured":"Xu Q, Xu Z, Philip J, et\u00a0al (2022) Point-NeRF: point-based neural radiance fields. In: IEEE\/CVF conference on computer vision and pattern recognition, pp 5438\u20135448. https:\/\/doi.org\/10.1109\/CVPR52688.2022.00536","DOI":"10.1109\/CVPR52688.2022.00536"},{"key":"11654_CR28","doi-asserted-by":"publisher","unstructured":"Yao Y, Luo Z, Li S, et\u00a0al (2020) BlendedMVS: a large-scale dataset for generalized multi-view stereo networks. In: IEEE\/CVF conference on computer vision and pattern recognition, pp 1787\u20131796. https:\/\/doi.org\/10.1109\/cvpr42600.2020.00186","DOI":"10.1109\/cvpr42600.2020.00186"},{"key":"11654_CR29","doi-asserted-by":"publisher","unstructured":"Yen-Chen L, Florence P, Barron JT, et\u00a0al (2021) iNeRF: inverting neural radiance fields for pose estimation. In: IEEE\/RSJ international conference on intelligent robots and systems (IROS), pp 1323\u20131330. https:\/\/doi.org\/10.1109\/IROS51168.2021.9636708","DOI":"10.1109\/IROS51168.2021.9636708"}],"container-title":["Neural Processing Letters"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11063-024-11654-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11063-024-11654-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11063-024-11654-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,31]],"date-time":"2024-08-31T16:11:23Z","timestamp":1725120683000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11063-024-11654-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,22]]},"references-count":29,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2024,8]]}},"alternative-id":["11654"],"URL":"https:\/\/doi.org\/10.1007\/s11063-024-11654-5","relation":{},"ISSN":["1573-773X"],"issn-type":[{"type":"electronic","value":"1573-773X"}],"subject":[],"published":{"date-parts":[[2024,7,22]]},"assertion":[{"value":"20 May 2024","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 July 2024","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"}}],"article-number":"214"}}