微信服务号

微信订阅号

2025年6月14日 21:24 星期六
首页 > 过刊浏览>2025年第36卷第4期 >1692-1714. DOI:10.13328/j.cnki.jos.007248
PDF HTML阅读 XML下载 导出引用 引用提醒
基于深度学习的多视图立体视觉综述
作者:
基金项目:

中国科学院基础前沿科学研究计划(22E0223301); 中国科学院青年创新促进会项目(E1213A02)


Survey on Multi-view Stereo Based on Deep Learning
Author:
  • 摘要
    • | |
  • 访问统计
    • |
  • 参考文献 [85]
    • |
  • 相似文献 [20]
    • | | |
  • 文章评论
    摘要:

    多视图立体视觉在自动驾驶、增强现实、遗产保护和生物医学等领域得到广泛应用. 为了弥补传统多视图立体视觉方法对低纹理区域不敏感、重建完整度差等不足, 基于深度学习的多视图立体视觉方法应运而生. 对基于深度学习的多视图立体视觉方法的开创性工作和发展现状进行综述, 重点关注基于深度学习的多视图立体视觉局部功能改进和整体架构改进方法, 深入分析代表性模型. 同时, 阐述目前广泛使用的数据集及评价指标, 并对比现有方法在数据集上的测试性能. 最后对多视图立体视觉未来有前景的研究发展方向进行展望.

    Abstract:

    Multi-view stereo (MVS) is widely used in fields such as autonomous driving, augmented reality, heritage conservation, and biomedicine. To address the limitations of traditional MVS methods, such as insensitivity to low-texture regions and poor reconstruction integrity, deep learning-based MVS methods have been proposed. This study reviews the pioneering work and current development of deep learning-based MVS methods. In particular, it focuses on methods for local functional improvement and overall architectural improvement and analyzes representative models. Meanwhile, the study describes widely used datasets and evaluation metrics and compares the test performance of existing methods on the datasets. Finally, promising research directions for MVS are presented.

    参考文献
    [1] 彭勇, 王爱迪, 王婷婷, 李京龙, 王占秋, 赵洋, 王子霖, 赵政. 面向生物控制的鲤鱼脑组织及脑电极三维重建. 生物医学工程学杂志, 2020, 37(5): 885–891.
    Peng Y, Wang AD, Wang TT, Li JL, Wang ZQ, Zhao Y, Wang ZL, Zhao Z. Three-dimensional reconstruction of carp brain tissue and brain electrodes for biological control. Journal of Biomedical Engineering, 2020, 37(5): 885–891 (in Chinese with English abstract).
    [2] Nicholson DT, Chalk C, Funnell WRJ, Daniel SJ. Can virtual reality improve anatomy education? A randomised controlled study of a computer-generated three-dimensional anatomical ear model. Medical Education, 2006, 40(11): 1081–1087.
    [3] Qu YF, Huang JY, Zhang X. Rapid 3D reconstruction for image sequence acquired from UAV camera. Sensors, 2018, 18(1): 225.
    [4] Carvajal-Ramírez F, Navarro-Ortega AD, Agüera-Vega F, Martínez-Carricondo P, Mancini F. Virtual reconstruction of damaged archaeological sites based on unmanned aerial vehicle photogrammetry and 3D modelling. Study case of a southeastern Iberia production area in the Bronze Age. Measurement, 2019, 136: 225–236.
    [5] Gao ZP, Zhai GT, Deng HW, Yang XK. Extended geometric models for stereoscopic 3D with vertical screen disparity. Displays, 2020, 65: 101972.
    [6] Wang X, Wang C, Liu B, Zhou XQ, Zhang L, Zheng J, Bai X. Multi-view stereo in the deep learning era: A comprehensive review. Displays, 2021, 70: 102102.
    [7] Furukawa Y, Hernández C. Multi-view stereo: A tutorial. Foundations and Trends® in Computer Graphics and Vision, 2015, 9(1–2): 1–148.
    [8] Žbontar J, LeCun Y. Computing the stereo matching cost with a convolutional neural network. In: Proc. of the 2015 IEEE Conf. on Computer Vision and Pattern Recognition. Boston: IEEE, 2015. 1592–1599. [doi: 10.1109/CVPR.2015.7298767]
    [9] Zagoruyko S, Komodakis N. Learning to compare image patches via convolutional neural networks. In: Proc. of the 2015 IEEE Conf. on Computer Vision and Pattern Recognition. Boston: IEEE, 2015. 4353–4361. [doi: 10.1109/CVPR.2015.7299064]
    [10] Han XF, Leung T, Jia YQ, Sukthankar R, Berg AC. MatchNet: Unifying feature and metric learning for patch-based matching. In: Proc. of the 2015 IEEE Conf. on Computer Vision and Pattern Recognition. Boston: IEEE, 2015. 3279–3286. [doi: 10.1109/CVPR.2015.7298948]
    [11] Murphy K, Schölkopf B, Žbontar J, LeCun Y. Stereo matching by training a convolutional neural network to compare image patches. The Journal of Machine Learning Research, 2016, 17(1): 2287–2318.
    [12] Güney F, Geiger A. Displets: Resolving stereo ambiguities using object knowledge. In: Proc. of the 2015 IEEE Conf. on Computer Vision and Pattern Recognition. Boston: IEEE, 2015. 4165–4175. [doi: 10.1109/CVPR.2015.7299044]
    [13] Luo WJ, Schwing AG, Urtasun R. Efficient deep learning for stereo matching. In: Proc. of the 2016 IEEE Conf. on Computer Vision and Pattern Recognition. Las Vegas: IEEE, 2016. 5695–5703. [doi: 10.1109/CVPR.2016.614]
    [14] Ji MQ, Gall J, Zheng HT, Liu YB, Fang L. SurfaceNet: An end-to-end 3D neural network for multiview stereopsis. In: Proc. of the 2017 IEEE Int’l Conf. on Computer Vision. Venice: IEEE, 2017. 2326–2334. [doi: 10.1109/ICCV.2017.253]
    [15] Yao Y, Luo ZX, Li SW, Fang T, Quan L. MVSNet: Depth inference for unstructured multi-view stereo. In: Proc. of the 15th European Conf. on Computer Vision. Munich: Springer, 2018. 785–801. [doi: 10.1007/978-3-030-01237-3_47]
    [16] Khot T, Agrawal S, Tulsiani S, Mertz C, Lucey S, Hebert M. Learning unsupervised multi-view stereopsis via robust photometric consistency. arXiv:1905.02706, 2019.
    [17] Chen AP, Xu ZX, Zhao FQ, Zhang XS, Xiang FB, Yu JY, Su H. MVSNeRF: Fast generalizable radiance field reconstruction from multi-view stereo. In: Proc. of the 2021 IEEE/CVF Int’l Conf. on Computer Vision. Montreal: IEEE, 2021. 14104–14113.
    [18] Cheng K, Long XX, Yang KZ, Yao Y, Yin W, Ma YX, Wang WP, Chen XJ. GaussianPro: 3D Gaussian splatting with progressive propagation. arXiv:2402.14650, 2024.
    [19] Choy CB, Xu DF, Gwak J, Chen K, Savarese S. 3D-R2N2: A unified approach for single and multi-view 3D object reconstruction. In: Proc. of the 14th European Conf. on Computer Vision. Amsterdam: Springer, 2016. 628–644. [doi: 10.1007/978-3-319-46484-8_38]
    [20] Kar A, Häne C, Malik J. Learning a multi-view stereo machine. In: Proc. of the 31st Int’l Conf. on Neural Information Processing Systems. Long Beach: Curran Associates Inc., 2017. 364–375.
    [21] Paschalidou D, Ulusoy AO, Schmitt C, van Gool L, Geiger A. RayNet: Learning volumetric 3D reconstruction with ray potentials. In: Proc. of the 2018 IEEE/CVF Conf. on Computer Vision and Pattern Recognition. Salt Lake City: IEEE, 2018. 3897–3906.
    [22] Ji MQ, Zhang JZ, Dai QH, Fang L. SurfaceNet+: An end-to-end 3D neural network for very sparse multi-view stereopsis. IEEE Trans. on Pattern Analysis and Machine Intelligence, 2021, 43(11): 4078–4093.
    [23] Jensen R, Dahl A, Vogiatzis G, Tola E, Aanæs H. Large scale multi-view stereopsis evaluation. In: Proc. of the 2014 IEEE Conf. on Computer Vision and Pattern Recognition. Columbus: IEEE, 2014. 406–413. [doi: 10.1109/CVPR.2014.59]
    [24] Xue YZ, Chen JS, Wan WT, Huang YQ, Yu C, Li TP, Bao JY. MVSCRF: Learning multi-view stereo with conditional random fields. In: Proc. of the 2019 IEEE/CVF Int’l Conf. on Computer Vision. Seoul: IEEE, 2019. 4311–4320. [doi: 10.1109/ICCV.2019.00441]
    [25] Yang JY, Mao W, Alvarez JM, Liu MM. Cost volume pyramid based depth inference for multi-view stereo. IEEE Trans. on Pattern Analysis and Machine Intelligence, 2022, 44(9): 4748–4760.
    [26] Wei ZH, Zhu QT, Min C, Chen YS, Wang GP. AA-RMVSNet: Adaptive aggregation recurrent multi-view stereo network. In: Proc. of the 2021 IEEE/CVF Int’l Conf. on Computer Vision. Montreal: IEEE, 2021. 6167–6176. [doi: 10.1109/ICCV48922.2021.00613]
    [27] Cai YC, Li L, Wang D, Liu XP. MFNet: Multi-level fusion aware feature pyramid based multi-view stereo network for 3D reconstruction. Applied Intelligence, 2023, 53(4): 4289–4301.
    [28] Zhang T. SuperMVS: Non-uniform cost volume for high-resolution multi-view stereo. arXiv:2203.14331, 2022.
    [29] Yan JF, Wei ZZ, Yi HW, Ding MY, Zhang RZ, Chen YS, Wang GP, Tai YW. Dense hybrid recurrent multi-view stereo net with dynamic consistency checking. In: Proc. of the 16th European Conf. on Computer Vision. Glasgow: Springer, 2020. 674–689. [doi: 10.1007/978-3-030-58548-8_39]
    [30] Cheng W, Bai ZY, Li JJ, Liu HJ, Yang LF. ADIM-MVSNet: Adaptive depth interval multi-view stereo network for 3D reconstruction. In: Proc. of the 5th Int’l Conf. on Image and Graphics Processing. Beijing: ACM, 2022. 281–287. [doi: 10.1145/3512388.3512429]
    [31] Zhang XD, Yang FZ, Chang M, Qin XF. MG-MVSNet: Multiple granularities feature fusion network for multi-view stereo. Neurocomputing, 2023, 528: 35–47.
    [32] Yu AZ, Guo WY, Liu B, Chen X, Wang X, Cao XF, Jiang BC. Attention aware cost volume pyramid based multi-view stereo network for 3D reconstruction. ISPRS Journal of Photogrammetry and Remote Sensing, 2021, 175: 448–460.
    [33] Li Y, Li WY, Zhao ZJ, Fan JH. DRI-MVSNet: A depth residual inference network for multi-view stereo images. PLoS One, 2022, 17(3): e0264721.
    [34] Weilharter R, Fraundorfer F. ATLAS-MVSNet: Attention layers for feature extraction and cost volume regularization in multi-view stereo. In: Proc. of the 26th Int’l Conf. on Pattern Recognition. Montreal: IEEE, 2022. 3557–3563.
    [35] Ding YK, Yuan WT, Zhu QT, Zhang HT, Liu XY, Wang YJ, Liu X. TransMVSNet: Global context-aware multi-view stereo network with transformers. In: Proc. of the 2022 IEEE/CVF Conf. on Computer Vision and Pattern Recognition. New Orleans: IEEE, 2022. 8575–8584. [doi: 10.1109/CVPR52688.2022.00839]
    [36] Zhu J, Peng B, Li WQ, Shen HF, Zhang Z, Lei JJ. Multi-view stereo with transformer. arXiv:2112.00336, 2021.
    [37] Zhang XD, Hu YT, Wang HC, Cao XB, Zhang BC. Long-range attention network for multi-view stereo. In: Proc. of the 2021 IEEE Winter Conf. on Applications of Computer Vision. Waikoloa: IEEE, 2021. 3781–3790. [doi: 10.1109/WACV48630.2021.00383]
    [38] Cao CJ, Ren XL, Fu YW. MVSFormer: Multi-view stereo by learning robust image features and temperature-based depth. arXiv:2208.02541, 2022.
    [39] Xu QS, Tao WB. PVSNet: Pixelwise visibility-aware multi-view stereo network. arXiv:2007.07714, 2020.
    [40] Wang FJH, Galliani S, Vogel C, Speciale P, Pollefeys M. PatchmatchNet: Learned multi-view patchmatch stereo. In: Proc. of the 2021 IEEE/CVF Conf. on Computer Vision and Pattern Recognition. Nashville: IEEE, 2021. 14189–14198.
    [41] Li Y, Zhao ZJ, Fan JH, Li WY. ADR-MVSNet: A cascade network for 3D point cloud reconstruction with pixel occlusion. Pattern Recognition, 2022, 125: 108516.
    [42] Yi HW, Wei ZZ, Ding MY, Zhang RZ, Chen YS, Wang GP, Tai YW. Pyramid multi-view stereo net with self-adaptive view aggregation. In: Proc. of the 2020 European Conf. on Computer Vision. Glasgow: Springer, 2020. 766–782. [doi: 10.1007/978-3-030-58545-7_44]
    [43] Peng R, Wang RJ, Wang ZY, Lai YW, Wang RG. Rethinking depth estimation for multi-view stereo: A unified representation. In: Proc. of the 2022 IEEE/CVF Conf. on Computer Vision and Pattern Recognition. New Orleans: IEEE, 2022. 8635–8644.
    [44] Wang XF, Zhu Z, Huang G, Qin FB, Ye Y, He YJ, Chi X, Wang XG. MVSTER: Epipolar transformer for efficient multi-view stereo. In: Proc. of the 17th European Conf. on Computer Vision. Tel Aviv: Springer, 2022. 573–591. [doi: 10.1007/978-3-031-19821-2_33]
    [45] Liao JL, Ding YK, Shavit Y, Huang DH, Ren SH, Guo J, Feng WS, Zhang K. WT-MVSNet: Window-based Transformers for multi-view stereo. Advances in Neural Information Processing Systems, 2022, 35: 8564–8576.
    [46] Liu YM, Rao Y, Rigall E, Fan H, Dong JY. Incorporating co-visibility reasoning into surface depth measurement. IEEE Trans. on Instrumentation and Measurement, 2023, 72: 5009912.
    [47] Xu QS, Tao WB. Learning inverse depth regression for multi-view stereo with correlation cost volume. In: Proc. of the 34th AAAI Conf. on Artificial Intelligence. New York: AAAI, 2020. 12508–12515. [doi: 10.1609/aaai.v34i07.6939]
    [48] Gu XD, Fan ZW, Zhu SY, Dai ZZ, Tan FT, Tan P. Cascade cost volume for high-resolution multi-view stereo and stereo matching. In: Proc. of the 2020 IEEE/CVF Conf. on Computer Vision and Pattern Recognition. Seattle: IEEE, 2020. 2492–2501.
    [49] Cheng S, Xu ZX, Zhu SL, Li ZW, Li LE, Ramamoorthi R, Su H. Deep stereo using adaptive thin volume representation with uncertainty awareness. In: Proc. of the 2020 IEEE/CVF Conf. on Computer Vision and Pattern Recognition. Seattle: IEEE, 2020. 2521–2531. [doi: 10.1109/CVPR42600.2020.00260]
    [50] Ma XJ, Gong Y, Wang QR, Huang JW, Chen L, Yu F. EPP-MVSNet: Epipolar-assembling based depth prediction for multi-view stereo. In: Proc. of the 2021 IEEE/CVF Int’l Conf. on Computer Vision. Montreal: IEEE, 2021. 5712–5720. [doi: 10.1109/ICCV48922.2021.00568]
    [51] Yang JY, Alvarez JM, Liu MM. Non-parametric depth distribution modelling based depth inference for multi-view stereo. In: Proc. of the 2022 IEEE/CVF Conf. on Computer Vision and Pattern Recognition. New Orleans: IEEE, 2022. 8616–8624.
    [52] Yao Y, Luo ZX, Li SW, Shen TW, Fang T, Quan L. Recurrent MVSNet for high-resolution multi-view stereo depth inference. In: Proc. of the 2019 IEEE/CVF Conf. on Computer Vision and Pattern Recognition. Long Beach: IEEE, 2019. 5520–5529.
    [53] Chen R, Han SF, Xu J, Su H. Visibility-aware point-based multi-view stereo network. IEEE Trans. on Pattern Analysis and Machine Intelligence, 2021, 43(10): 3695–3708.
    [54] Weilharter R, Fraundorfer F. HighRes-MVSNet: A fast multi-view stereo network for dense 3D reconstruction from high-resolution images. IEEE Access, 2021, 9: 11306–11315.
    [55] Luo KY, Guan T, Ju LL, Huang HP, Luo YW. P-MVSNet: Learning patch-wise matching confidence aggregation for multi-view stereo. In: Proc. of the 2019 IEEE/CVF Int’l Conf. on Computer Vision. Seoul: IEEE, 2019. 10451–10460. [doi: 10.1109/ICCV.2019.01055]
    [56] Yu ZH, Gao SH. Fast-MVSNet: Sparse-to-dense multi-view stereo with learned propagation and gauss-newton refinement. In: Proc. of the 2020 IEEE/CVF Conf. on Computer Vision and Pattern Recognition. Seattle: IEEE, 2020. 1946–1955.
    [57] Wang FJH, Galliani S, Vogel C, Pollefeys M. IterMVS: Iterative probability estimation for efficient multi-view stereo. In: Proc. of the 2022 IEEE/CVF Conf. on Computer Vision and Pattern Recognition. New Orleans: IEEE, 2022. 8596–8605.
    [58] Rich A, Stier N, Sen P, Höllerer T. 3DVNet: Multi-view depth prediction and volumetric refinement. In: Proc. of the 2021 Int’l Conf. on 3D Vision. London: IEEE, 2021. 700–709. [doi: 10.1109/3DV53792.2021.00079]
    [59] Dai YC, Zhu ZD, Rao ZB, Li B. MVS2: Deep unsupervised multi-view stereo with multi-view symmetry. In: Proc. of the 2019 Int’l Conf. on 3D Vision. Quebec City: IEEE, 2019. 1–8. [doi: 10.1109/3DV.2019.00010]
    [60] Mallick A, Stückler J, Lensch HPA. Learning to adapt multi-view stereo by self-supervision. In: Proc. of the 31st British Machine Vision Conf. BMVA Press, 2020.
    [61] Huang BC, Yi HW, Huang C, He YJ, Liu JB, Liu X. M3VSNET: Unsupervised multi-metric multi-view stereo network. In: Proc. of the 2021 IEEE Int’l Conf. on Image Processing. Anchorage: IEEE, 2021. 3163–3167. [doi: 10.1109/ICIP42928.2021.9506469]
    [62] Yang JY, Alvarez JM, Liu MM. Self-supervised learning of depth inference for multi-view stereo. In: Proc. of the 2021 IEEE/CVF Conf. on Computer Vision and Pattern Recognition. Nashville: IEEE, 2021. 7522–7530. [doi: 10.1109/CVPR46437.2021.00744]
    [63] Xu HB, Zhou ZP, Wang YL, Kang WX, Sun BG, Li H, Qiao Y. Digging into uncertainty in self-supervised multi-view stereo. In: Proc. of the 2021 IEEE/CVF Int’l Conf. on Computer Vision. Montreal: IEEE, 2021. 6058–6067. [doi: 10.1109/ICCV48922.2021.00602]
    [64] Dong HN, Yao J. PatchMVSNet: Patch-wise unsupervised multi-view stereo for weakly-textured surface reconstruction. arXiv:2203.02156, 2022.
    [65] Xu HB, Zhou ZP, Qiao Y, Kang WX, Wu QX. Self-supervised multi-view stereo via effective co-segmentation and data-augmentation. In: Proc. of the 35th AAAI Conf. on Artificial Intelligence. AAAI, 2021. 3030–3038.
    [66] Ding YK, Zhu QT, Liu XY, Yuan WT, Zhang HT, Zhang C. KD-MVS: Knowledge distillation based self-supervised learning for multi-view stereo. In: Proc. of the 17th European Conf. on Computer Vision. Tel Aviv: Springer, 2022. 630–646. [doi: 10.1007/978-3-031-19821-2_36]
    [67] Mildenhall B, Srinivasan PP, Tancik M, Barron JT, Ramamoorthi R, Ng R. NeRF: Representing scenes as neural radiance fields for view synthesis. In: Proc. of the 16th European Conf. on Computer Vision. Glasgow: Springer, 2020. 405–421. [doi: 10.1007/978-3-030-58452-8_24]
    [68] Rosu RA, Behnke S. NeuralMVS: Bridging multi-view stereo and novel view synthesis. In: Proc. of the 2022 Int’l Joint Conf. on Neural Networks. Padua: IEEE, 2022. 1–7. [doi: 10.1109/IJCNN55064.2022.9892024]
    [69] Xi JH, Shi YF, Wang YJ, Guo YL, Xu K. RayMVSNet: Learning ray-based 1D implicit fields for accurate multi-view stereo. In: Proc. of the 2022 IEEE/CVF Conf. on Computer Vision and Pattern Recognition. New Orleans: IEEE, 2022. 8585–8595.
    [70] Chang D, Božič A, Zhang T, Yan QS, Chen YC, Süsstrunk S, Nießner M. RC-MVSNet: Unsupervised multi-view stereo with neural rendering. In: Proc. of the 17th European Conf. on Computer Vision. Tel Aviv: Springer, 2022. 665–680. [doi: 10.1007/978-3-031-19821-2_38]
    [71] Wang P, Liu LJ, Liu Y, Theobalt C, Komura T, Wang WP. NeuS: Learning neural implicit surfaces by volume rendering for multi-view reconstruction. In: Proc. of the 35th Int’l Conf. on Neural Information Processing Systems. Curran Associates Inc., 2021. 2081.
    [72] Yariv L, Gu JT, Kasten Y, Lipman Y. Volume rendering of neural implicit surfaces. In: Proc. of the 35th Int’l Conf. on Neural Information Processing Systems. Curran Associates Inc., 2021. 367.
    [73] Oechsle M, Peng SY, Geiger A. UNISURF: Unifying neural implicit surfaces and radiance fields for multi-view reconstruction. In: Proc. of the 2021 IEEE/CVF Int’l Conf. on Computer Vision. Montreal: IEEE, 2021. 5569–5579. [doi: 10.1109/ICCV48922.2021.00554]
    [74] Long XX, Lin C, Wang P, Komura T, Wang WP. SparseNeuS: Fast generalizable neural surface reconstruction from sparse views. In: Proc. of the 17th European Conf. on Computer Vision. Tel Aviv: Springer, 2022. 210–227. [doi: 10.1007/978-3-031-19824-3_13]
    [75] Wu HY, Graikos A, Samaras D. S-VolSDF: Sparse multi-view stereo regularization of neural implicit surfaces. In: Proc. of the 2023 IEEE/CVF Int’l Conf. on Computer Vision. Paris: IEEE, 2023. 3533–3545. [doi: 10.1109/ICCV51070.2023.00329]
    [76] Ren YF, Wang FJH, Zhang T, Pollefeys M, Süsstrunk S. VolRecon: Volume rendering of signed ray distance functions for generalizable multi-view reconstruction. In: Proc. of the 2023 IEEE/CVF Conf. on Computer Vision and Pattern Recognition. Vancouver: IEEE, 2023. 16685–16695. [doi: 10.1109/CVPR52729.2023.01601]
    [77] Kerbl B, Kopanas G, Leimkuehler T, Drettakis G. 3D Gaussian splatting for real-time radiance field rendering. ACM Trans. on Graphics (TOG), 2023, 42(4): 139.
    [78] Seitz SM, Curless B, Diebel J, Scharstein D, Szeliski R. A comparison and evaluation of multi-view stereo reconstruction algorithms. In: Proc. of the 2006 IEEE Computer Society Conf. on Computer Vision and Pattern Recognition. New York: IEEE, 2006. 519–528. [doi: 10.1109/CVPR.2006.19]
    [79] Strecha C, von Hansen W, Van Gool L, Fua P, Thoennessen U. On benchmarking camera calibration and multi-view stereo for high resolution imagery. In: Proc. of the 2008 IEEE Conf. on Computer Vision and Pattern Recognition. Anchorage: IEEE, 2008. 1–8. [doi: 10.1109/CVPR.2008.4587706]
    [80] Knapitsch A, Park J, Zhou QY, Koltun V. Tanks and temples: Benchmarking large-scale scene reconstruction. ACM Trans. on Graphics (TOG), 2017, 36(4): 78.
    [81] Schöps T, Schönberger JL, Galliani S, Sattler T, Schindler K, Pollefeys M, Geiger A. A multi-view stereo benchmark with high-resolution images and multi-camera videos. In: Proc. of the 2017 IEEE Conf. on Computer Vision and Pattern Recognition. Honolulu: IEEE, 2017. 2538–2547. [doi: 10.1109/CVPR.2017.272]
    [82] Yao Y, Luo ZX, Li SW, Zhang JY, Ren YF, Zhou L, Fang T, Quan L. BlendedMVS: A large-scale dataset for generalized multi-view stereo networks. In: Proc. of the 2020 IEEE/CVF Conf. on Computer Vision and Pattern Recognition. Seattle: IEEE, 2020. 1787–1796. [doi: 10.1109/CVPR42600.2020.00186]
    [83] Chen PH, Yang HC, Chen KW, Chen YS. MVSNet++: Learning depth-based attention pyramid features for multi-view stereo. IEEE Trans. on Image Processing, 2020, 29: 7261–7273.
    [84] Zhang JZ, Ji MQ, Wang GY, Xue ZW, Wang SJ, Fang L. SurRF: Unsupervised multi-view stereopsis by learning surface radiance field. IEEE Trans. on Pattern Analysis and Machine Intelligence, 2022, 44(11): 7912–7927.
    引证文献
    网友评论
    网友评论
    分享到微博
    发 布
引用本文

樊铭瑞,申冰可,牛文龙,彭晓东,谢文明,杨震.基于深度学习的多视图立体视觉综述.软件学报,2025,36(4):1692-1714

复制
分享
文章指标
  • 点击次数:296
  • 下载次数: 650
  • HTML阅读次数: 154
  • 引用次数: 0
历史
  • 收稿日期:2023-06-28
  • 最后修改日期:2024-02-08
  • 在线发布日期: 2024-12-31
文章二维码
友情链接:中国科学院软件研究所中国计算机学会中国科学院国家自然科学基金委员会CCF数字图书馆Int'l J of Softw Info计算机系统应用
您是第20047223位访问者
版权所有：中国科学院软件研究所 京ICP备05046678号-3
地址：北京市海淀区中关村南四街4号,邮政编码：100190
电话：010-62562563 传真：010-62562533 Email：jos@iscas.ac.cn
技术支持：北京勤云科技发展有限公司

京公网安备 11040202500063号