{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,22]],"date-time":"2026-01-22T21:07:46Z","timestamp":1769116066238,"version":"3.49.0"},"reference-count":36,"publisher":"MDPI AG","issue":"6","license":[{"start":{"date-parts":[[2024,3,16]],"date-time":"2024-03-16T00:00:00Z","timestamp":1710547200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Neural radiance fields (NeRFs) leverage a neural representation to encode scenes, obtaining photorealistic rendering of novel views. However, NeRF has notable limitations. A significant drawback is that it does not capture surface geometry and only renders the object surface colors. Furthermore, the training of NeRF is exceedingly time-consuming. We propose Depth-NeRF as a solution to these issues. Specifically, our approach employs a fast depth completion algorithm to denoise and complete the depth maps generated by RGB-D cameras. These improved depth maps guide the sampling points of NeRF to be distributed closer to the scene\u2019s surface, benefiting from dense depth information. Furthermore, we have optimized the network structure of NeRF and integrated depth information to constrain the optimization process, ensuring that the termination distribution of the ray is consistent with the scene\u2019s geometry. Compared to NeRF, our method accelerates the training speed by 18%, and the rendered images achieve a higher PSNR than those obtained by mainstream methods. Additionally, there is a significant reduction in RMSE between the rendered scene depth and the ground truth depth, which indicates that our method can better capture the geometric information of the scene. With these improvements, we can train the NeRF model more efficiently and achieve more accurate rendering results.<\/jats:p>","DOI":"10.3390\/s24061919","type":"journal-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T04:25:15Z","timestamp":1710735915000},"page":"1919","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Enhancing View Synthesis with Depth-Guided Neural Radiance Fields and Improved Depth Completion"],"prefix":"10.3390","volume":"24","author":[{"given":"Bojun","family":"Wang","sequence":"first","affiliation":[{"name":"School of Automation, Wuhan University of Technology, Wuhan 430070, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Danhong","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Automation, Wuhan University of Technology, Wuhan 430070, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yixin","family":"Su","sequence":"additional","affiliation":[{"name":"School of Automation, Wuhan University of Technology, Wuhan 430070, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huajun","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Automation, Wuhan University of Technology, Wuhan 430070, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2024,3,16]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"45","DOI":"10.1111\/cgf.14340","article-title":"DONeRF: Towards Real-Time Rendering of Compact Neural Radiance Fields using Depth Oracle Networks","volume":"40","author":"Neff","year":"2021","journal-title":"Comput. Graph. Forum"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Hu, T., Liu, S., Chen, Y., Shen, T., and Jia, J. (2022). EfficientNeRF: Efficient Neural Radiance Fields. arXiv.","DOI":"10.1109\/CVPR52688.2022.01256"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Mildenhall, B., Srinivasan, P.P., Tancik, M., Barron, J.T., Ramamoorthi, R., and Ng, R. (2020). NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis. arXiv.","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Gafni, G., Thies, J., Zollhofer, M., and Niesner, M. (2021, January 20\u201325). Dynamic Neural Radiance Fields for Monocular 4D Facial Avatar Reconstruction. Proceedings of the 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA.","DOI":"10.1109\/CVPR46437.2021.00854"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Tretschk, E., Tewari, A., Golyanik, V., Zollhofer, M., Lassner, C., and Theobalt, C. (2021, January 11\u201317). Non-Rigid Neural Radiance Fields: Reconstruction and Novel View Synthesis of a Dynamic Scene From Monocular Video. Proceedings of the 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), Montreal, BC, Canada.","DOI":"10.1109\/ICCV48922.2021.01272"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Pumarola, A., Corona, E., Pons-Moll, G., and Moreno-Noguer, F. (2021, January 20\u201325). D-NeRF: Neural Radiance Fields for Dynamic Scenes. Proceedings of the 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA.","DOI":"10.1109\/CVPR46437.2021.01018"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Tancik, M., Mildenhall, B., Wang, T., Schmidt, D., Srinivasan, P.P., Barron, J.T., and Ng, R. (2021, January 20\u201325). Learned Initializations for Optimizing Coordinate-Based Neural Representations. Proceedings of the 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA.","DOI":"10.1109\/CVPR46437.2021.00287"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Chan, E.R., Monteiro, M., Kellnhofer, P., Wu, J., and Wetzstein, G. (2021, January 20\u201325). pi-GAN: Periodic Implicit Generative Adversarial Networks for 3D-Aware Image Synthesis. Proceedings of the 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA.","DOI":"10.1109\/CVPR46437.2021.00574"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Yu, A., Ye, V., Tancik, M., and Kanazawa, A. (2021). pixelNeRF: Neural Radiance Fields from One or Few Images. arXiv.","DOI":"10.1109\/CVPR46437.2021.00455"},{"key":"ref_10","unstructured":"Schwarz, K., Liao, Y., Niemeyer, M., and Geiger, A. (2021). GRAF: Generative Radiance Fields for 3D-Aware Image Synthesis. arXiv."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3306346.3323020","article-title":"Neural volumes: Learning dynamic renderable volumes from images","volume":"38","author":"Lombardi","year":"2019","journal-title":"ACM Trans. Graph."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"377","DOI":"10.1111\/cgf.13369","article-title":"Single-image Tomography: 3D Volumes from 2D Cranial X-rays","volume":"37","author":"Henzler","year":"2018","journal-title":"Comput. Graph. Forum"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Sitzmann, V., Thies, J., Heide, F., NieBner, M., Wetzstein, G., and Zollhofer, M. (2019, January 15\u201320). DeepVoxels: Learning Persistent 3D Feature Embeddings. Proceedings of the 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00254"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Martin-Brualla, R., Pandey, R., Yang, S., Pidlypenskyi, P., Taylor, J., Valentin, J., Khamis, S., Davidson, P., Tkach, A., and Lincoln, P. (2018). LookinGood: Enhancing Performance Capture with Real-time Neural Re-Rendering. arXiv.","DOI":"10.1145\/3272127.3275099"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Yariv, L., Hedman, P., Reiser, C., Verbin, D., Srinivasan, P.P., Szeliski, R., Barron, J.T., and Mildenhall, B. (2023, January 6\u201310). BakedSDF: Meshing Neural SDFs for Real-Time View Synthesis. Proceedings of the ACM SIGGRAPH 2023 Conference Proceedings, Los Angeles, CA, USA.","DOI":"10.1145\/3588432.3591536"},{"key":"ref_16","first-page":"25018","article-title":"MonoSDF: Exploring Monocular Geometric Cues for Neural Implicit Surface Reconstruction","volume":"35","author":"Yu","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Li, Z., M\u00fcller, T., Evans, A., Taylor, R.H., Unberath, M., Liu, M.-Y., and Lin, C.-H. (2023). Neuralangelo: High-Fidelity Neural Surface Reconstruction. arXiv.","DOI":"10.1109\/CVPR52729.2023.00817"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Wei, Y., Liu, S., Rao, Y., Zhao, W., Lu, J., and Zhou, J. (2021, January 11\u201317). NerfingMVS: Guided Optimization of Neural Radiance Fields for Indoor Multi-view Stereo. Proceedings of the 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), Montreal, BC, Canada.","DOI":"10.1109\/ICCV48922.2021.00556"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Deng, K., Liu, A., Zhu, J.-Y., and Ramanan, D. (2022, January 18\u201324). Depth-supervised NeRF: Fewer Views and Faster Training for Free. Proceedings of the 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA.","DOI":"10.1109\/CVPR52688.2022.01254"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"34","DOI":"10.24132\/JWSCG.2022.5","article-title":"Mip-NeRF RGB-D: Depth Assisted Fast Neural Radiance Fields","volume":"30","author":"Dey","year":"2022","journal-title":"J. WSCG"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Barron, J.T., Mildenhall, B., Tancik, M., Hedman, P., Martin-Brualla, R., and Srinivasan, P.P. (2021, January 11\u201317). Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fields. Proceedings of the 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), Montreal, BC, Canada.","DOI":"10.1109\/ICCV48922.2021.00580"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Azinovic, D., Martin-Brualla, R., Goldman, D.B., Niebner, M., and Thies, J. (2022, January 18\u201324). Neural RGB-D Surface Reconstruction. Proceedings of the 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA.","DOI":"10.1109\/CVPR52688.2022.00619"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Garbin, S.J., Kowalski, M., Johnson, M., Shotton, J., and Valentin, J. (2021). FastNeRF: High-Fidelity Neural Rendering at 200FPS. arXiv.","DOI":"10.1109\/ICCV48922.2021.01408"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Reiser, C., Peng, S., Liao, Y., and Geiger, A. (2021). KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPs. arXiv.","DOI":"10.1109\/ICCV48922.2021.01407"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Yu, A., Li, R., Tancik, M., Li, H., Ng, R., and Kanazawa, A. (2021). PlenOctrees for Real-time Rendering of Neural Radiance Fields. arXiv.","DOI":"10.1109\/ICCV48922.2021.00570"},{"key":"ref_26","unstructured":"Liu, L., Gu, J., Lin, K.Z., Chua, T.-S., and Theobalt, C. (2021). Neural Sparse Voxel Fields. arXiv."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Hedman, P., Srinivasan, P.P., Mildenhall, B., Barron, J.T., and Debevec, P. (2021, January 11\u201317). Baking Neural Radiance Fields for Real-Time View Synthesis. Proceedings of the 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), Montreal, BC, Canada.","DOI":"10.1109\/ICCV48922.2021.00582"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Chen, A., Xu, Z., Zhao, F., Zhang, X., Xiang, F., Yu, J., and Su, H. (2021, January 11\u201317). MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereo. Proceedings of the 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), Montreal, BC, Canada.","DOI":"10.1109\/ICCV48922.2021.01386"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Ferrari, V., Hebert, M., Sminchisescu, C., and Weiss, Y. (2018). Computer Vision\u2014ECCV 2018, Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany, 8\u201314 September 2018, Springer International Publishing.","DOI":"10.1007\/978-3-030-01234-2"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Schonberger, J.L., and Frahm, J.-M. (2016, January 27\u201330). Structure-from-Motion Revisited. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.445"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Ku, J., Harakeh, A., and Waslander, S.L. (2018). In Defense of Classical Image Processing: Fast Depth Completion on the CPU. arXiv.","DOI":"10.1109\/CRV.2018.00013"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"600","DOI":"10.1109\/TIP.2003.819861","article-title":"Image Quality Assessment: From Error Visibility to Structural Similarity","volume":"13","author":"Wang","year":"2004","journal-title":"IEEE Trans. Image Process."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Zhang, R., Isola, P., Efros, A.A., Shechtman, E., and Wang, O. (2018, January 18\u201322). The Unreasonable Effectiveness of Deep Features as a Perceptual Metric. Proceedings of the 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref_34","first-page":"1","article-title":"Instant neural graphics primitives with a multiresolution hash encoding","volume":"41","author":"Evans","year":"2022","journal-title":"ACM Trans. Graph."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Dai, A., Chang, A.X., Savva, M., Halber, M., Funkhouser, T., and Niessner, M. (2017, January 21\u201326). ScanNet: Richly-Annotated 3D Reconstructions of Indoor Scenes. Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.261"},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Zeng, A., Song, S., Niessner, M., Fisher, M., Xiao, J., and Funkhouser, T. (2017, January 21\u201326). 3DMatch: Learning Local Geometric Descriptors from RGB-D Reconstructions. Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.29"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/24\/6\/1919\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T14:14:49Z","timestamp":1760105689000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/24\/6\/1919"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3,16]]},"references-count":36,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2024,3]]}},"alternative-id":["s24061919"],"URL":"https:\/\/doi.org\/10.3390\/s24061919","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,3,16]]}}}