[1] Y FURUKAWA, C HERNÁNDEZ. Multi-view stereo： a tutorial. Foundations and Trends® in Computer Graphics and Vision, 9, 1-148(2015).

[2] M W SMITH, J L CARRIVICK, D J QUINCEY. Structure from motion photogrammetry in physical geography. Progress in Physical Geography： Earth and Environment, 40, 247-275(2016).

[3] [3] 3刘东生， 陈建林， 费点， 等. 基于深度相机的大场景三维重建［J］. 光学 精密工程， 2020， 28（1）： 234-243. doi: 10.3788/ope.20202801.0234LIUD S， CHENJ L， FEID， et al. Three-dimensional reconstruction of large-scale scene based on depth camera［J］. Opt. Precision Eng.， 2020， 28（1）： 234-243.（in Chinese）. doi: 10.3788/ope.20202801.0234

[4] J L SCHÖNBERGER, E L ZHENG, J M FRAHM et al. Pixelwise View Selection for Unstructured Multi-View Stereo. Computer Vision - ECCV 2016, 501-518(2016).

[5] Q S XU, W B TAO. Multi-scale geometric consistency guided multi-view stereo, 5478-5487(15).

[6] [6] 6张宝祥， 玉振明， 杨秋慧. 基于Harris-SIFT算法和全卷积深度预测的显微镜成像的三维重建研究［J］. 光学 精密工程， 2022， 30（14）： 1669-1681. doi: 10.37188/OPE.20223014.1669ZHANGB X， YUZ M， YANGQ H. Research on 3D reconstruction of microscope imaging based on Harris-SIFT algorithm and full convolution depth prediction［J］. Opt. Precision Eng.， 2022， 30（14）： 1669-1681.（in Chinese）. doi: 10.37188/OPE.20223014.1669

[7] M Q JI, J GALL, H T ZHENG et al. SurfaceNet： an End-to-End 3D neural network for multiview stereopsis, 2326-2334(22).

[8] A KAR, C HÄNE, J MALIK. Learning a Multi-View Stereo Machine. arXiv, 1708-05375(2017). https：//arxiv.org/abs/1708.05375

[9] H AANÆS, R R JENSEN, G VOGIATZIS et al. Large-scale data for multiple-view stereopsis. International Journal of Computer Vision, 120, 153-168(2016).

[10] A KNAPITSCH, J PARK, Q Y ZHOU et al. Tanks and temples： benchmarking large-scale scene reconstruction. ACM Transactions on Graphics, 36, 1-13.

[11] Y YAO, Z X LUO, S W LI et al. MVSNet： Depth Inference for Unstructured Multi-View Stereo. Computer Vision-ECCV 2018, 785-801(2018).

[12] L Y LI, X Y LI, L Y JIANG et al. A review on deep learning techniques for cloud detection methodologies and challenges. Signal， Image and Video Processing, 15, 1527-1535(2021).

[13] Q ZHU, C MIN, Z WEI et al. Deep Learning for Multi-View Stereo via Plane Sweep： a Survey. arXiv, 2106-15328(2021). https：//arxiv.org/abs/2106.15328

[14] X WANG, C WANG, B LIU et al. Multi-view stereo in the deep learning era： a comprehensive review. Displays, 70, 102102(2021).

[15] D GALLUP, J M FRAHM, P MORDOHAI et al. Real-time plane-sweeping stereo with multiple sweeping directions, 1-8(17).

[16] Y YAO, Z X LUO, S W LI et al. Recurrent MVSNet for high-resolution multi-view stereo depth inference, 5520-5529(15).

[17] R CHEN, S F HAN, J XU et al. Point-based multi-view stereo network, 1538-1547.

[18] Y Z XUE, J S CHEN, W T WAN et al. MVSCRF： learning multi-view stereo with conditional random fields, 4311-4320.

[19] X D GU, Z W FAN, S Y ZHU et al. Cascade cost volume for high-resolution multi-view stereo and stereo matching, 2492-2501(13).

[20] J Y YANG, W MAO, J M ALVAREZ et al. Cost volume pyramid based depth inference for multi-view stereo, 4876-4885(13).

[21] O RONNEBERGER, P FISCHER, T BROX. U-net： Convolutional Networks for Biomedical Image Segmentation. Lecture Notes in Computer Science, 234-241(2015).

[22] J ZHANG, Y YAO, S LI et al. Visibility-Aware Multi-View Stereo Network. arXiv, 2008-07928(2020). https：//arxiv.org/abs/2008. 07928

[23] Y F SHI, J H XI, D W HU et al. RayMVSNet： learning ray-based 1D implicit fields for accurate multi-view stereo, 1-17(2023).

[24] H W YI, Z Z WEI, M Y DING et al. Pyramid Multi-View Stereo Net with Self-Adaptive View Aggregation. Computer Vision - ECCV 2020, 766-782(2020).

[25] F YU, V KOLTUN. Multi-Scale Context Aggregation by Dilated Convolutions. arXiv, 1511-07122(2015). https：//arxiv.org/abs/1511.07122

[26] T Y LIN, P DOLLÁR, R GIRSHICK et al. Feature pyramid networks for object detection, 936-944(21).

[27] S CHENG, Z X XU, S L ZHU et al. Deep stereo using adaptive thin volume representation with uncertainty awareness, 2521-2531(13).

[28] Y LI, W Y LI, Z J ZHAO et al. DRI-MVSNet： a depth residual inference network for multi-view stereo images. PLoS One, 17(2022).

[29] H LI, P XIONG, J AN et al. Pyramid Attention Network for Semantic Segmentation. arXiv, 1805-10180(2018). https：//arxiv.org/abs/1805.10180

[30] K ZHANG, M Y LIU, J L ZHANG et al. PA-MVSNet： sparse-to-dense multi-view stereo with pyramid attention. IEEE Access, 9, 27908-27915(2021).

[31] ANZHU， YU， et al, ANZHU， YU， et al. Attention aware cost volume pyramid based multi-view stereo network for 3D reconstruction. ISPRS Journal of Photogrammetry and Remote Sensing, 175, 448-460(2021).

[32] J J LI, Z Y BAI, W CHENG et al. Feature pyramid multi-view stereo network based on self-attention mechanism, 226-233(9).

[33] N PARMAR, P RAMACHANDRAN, A VASWANI et al. Stand-alone self-attention in vision models, 13(2019).

[34] X D ZHANG, Y T HU, H C WANG et al. Long-range attention network for multi-view stereo, 3781-3790(2021).

[35] W J LIU, J K WANG, H C QU et al. Hierarchical MVSNet with cost volume separation and fusion based on U-shape feature extraction. Multimedia Systems, 29, 377-387(2023).

[36] J PARK, J Y LEE et al. CBAM： Convolutional Block Attention Module. Computer Vision - ECCV 2018, 3-19(2018).

[37] C CAO, X REN, Y FU. MVSFormer： multi-view stereo with pre-trained vision transformers and temperature-based depth. arXiv preprint arXiv：, 2022.

[38] A DOSOVITSKIY, L BEYER, A KOLESNIKOV et al. An Image is Worth. arXiv, 2010-11929(2020). https：//arxiv.org/abs/2010.11929

[39] S SAEED, S LEE, Y CHO et al. ASPPMVSNet： a high-receptive-field multiview stereo network for dense three-dimensional reconstruction. ETRI Journal, 44, 1034-1046(2022).

[40] L C CHEN, G PAPANDREOU, I KOKKINOS et al. DeepLab： semantic image segmentation with deep convolutional nets， atrous convolution， and fully connected CRFs. IEEE Transactions on Pattern Analysis and Machine Intelligence, 40, 834-848(2018).

[41] Z Z WEI, Q T ZHU, C MIN et al. AA-RMVSNet： adaptive aggregation recurrent multi-view stereo network, 6167-6176(10).

[42] J E N MASSON, M R PETRY, D F COUTINHO et al. Deformable convolutions in multi-view stereo. Image and Vision Computing, 118, 104369(2022).

[43] W CHENG, Z Y BAI, J J LI et al. ADIM-MVSNet： adaptive depth interval multi-view stereo network for 3d reconstruction, 281-287(2022).

[44] J F DAI, H Z QI, Y W XIONG et al. Deformable convolutional networks, 764-773(22).

[45] Y K DING, W T YUAN, Q T ZHU et al. TransMVSNet： global context-aware multi-view stereo network with transformers, 8575-8584(18).

[46] KT GIANG, S SONG. Curvature-guided dynamic scale networks for multi-view stereo. arXiv preprint arXiv：, 2022.

[47] J F YAN, Z Z WEI, H W YI et al. Dense hybrid recurrent multi-view stereo net with dynamic consistency checking, 674-689(23).

[48] Z H YU, S H GAO. Fast-MVSNet： sparse-to-dense multi-view stereo with learned propagation and gauss-newton refinement, 1946-1955(13).

[49] R CHEN, S F HAN, J XU et al. Visibility-aware point-based multi-view stereo network. IEEE Transactions on Pattern Analysis and Machine Intelligence, 43, 3695-3708(2020).

[50] R WEILHARTER, F FRAUNDORFER. HighRes-MVSNet： a fast multi-view stereo network for dense 3D reconstruction from high-resolution images. IEEE Access, 9, 11306-11315(2021).

[51] P YI, S TANG, J YAO. DDR-Net： Learning Multi-Stage Multi-View Stereo with Dynamic Depth Range. arXiv, 2103-14275(2021). https：//arxiv.org/abs/2103.14275

[52] A VASWANI, N SHAZEER, N PARMAR et al. Attention is all you need, 6000-6010(9).

[53] X F WANG, Z ZHU, G HUANG et al. MVSTER： Epipolar Transformer for Efficient Multi-View Stereo. Lecture Notes in Computer Science, 573-591(2022).

[54] J ZHU, B PENG, W LI et al. Multi-view Stereo with Transformer. arXiv, 2112-00336(2021). https：//arxiv.org/abs/2112.00336

[55] J LIAO, Y DING, Y SHAVIT et al. WT-MVSNet： Window-Based Transformers for Multi-View Stereo. arXiv, 2205-14319(2022). https：//arxiv.org/abs/2205.14319

[56] Y H HE, R YAN, K FRAGKIADAKI et al. Epipolar transformers, 7776-7785(13).

[57] P H CHEN, H C YANG, K W CHEN et al. MVSNet： learning depth-based attention pyramid features for multi-view stereo. IEEE Transactions on Image Processing, 29, 7261-7273(2020).

[58] Y BENGIO, J LOURADOUR, R COLLOBERT et al. Curriculum learning, 41-48(18).

[59] X Y GUO, K YANG, W K YANG et al. Group-wise correlation stereo network, 3268-3277(15).

[60] Q S XU, W B TAO. Learning inverse depth regression for multi-view stereo with correlation cost volume. Proceedings of the AAAI Conference on Artificial Intelligence, 34, 12508-12515(2020).

[61] Q XU, W TAO. PVSNet： Pixelwise Visibility-Aware Multi-View Stereo Network. arXiv, 2007-07714(2020). https：//arxiv.org/abs/2007.07714

[62] F WANG, S GALLIANI, C VOGEL et al. PatchmatchNet： learned multi-view patchmatch stereo, 14189-14198(20).

[63] B SONG, X HU, J XIAO et al. Implicit neural refinement based multi-view stereo network with adaptive correlation. Image and Vision Computing, 124, 104511(2022).

[64] Y C CAI, L LI, D WANG et al. MFNet： Multi-level fusion aware feature pyramid based multi-view stereo network for 3D reconstruction. Applied Intelligence, 53, 4289-4301(2023).

[65] S Y GAO, Z X LI, Z Q WANG. Cost Volume Pyramid Network with Multi-Strategies Range Searching for Multi-View Stereo. Advances in Computer Graphics, 157-169(2022).

[66] K Y LUO, T GUAN, L L JU et al. P-MVSNet： learning patch-wise matching confidence aggregation for multi-view stereo, 10451-10460(2019).

[67] X J MA, Y GONG, Q R WANG et al. EPP-MVSNet： epipolar-assembling based depth prediction for multi-view stereo, 5712-5720(10).

[68] R PENG, R J WANG, Z Y WANG et al. Rethinking depth estimation for multi-view stereo： a unified representation, 8635-8644(18).

[69] H F XU, J Y ZHANG. AANet： adaptive aggregation network for efficient stereo matching, 1956-1965(13).

[70] C SORMANN, P KNÖBELREITER, A KUHN et al. BP-MVSNet： belief-propagation-layers for multi-view-stereo, 394-403(2021).

[71] Y QI, W SU, Q XU et al. Sparse prior guided deep multi-view stereo. Computers & Graphics, 107, 1-9(2022).

[72] J LIU, S P JI. A novel recurrent encoder-decoder structure for large-scale multi-view stereo reconstruction from an open aerial dataset, 6049-6058(13).

[73] Q XU, M R OSWALD, W TAO et al. Non-local recurrent regularization networks for multi-view stereo. arXiv preprint arXiv：, 2021.

[74] F WANG, S GALLIANI, C VOGEL et al. IterMVS： iterative probability estimation for efficient multi-view stereo, 8596-8605(18).

[75] Z X MI, C DI, D XU. Generalized binary search network for highly-efficient multi-view stereo, 12981-12990(18).

[76] J Y LEE, J DEGOL, C H ZOU et al. PatchMatch-RL： deep mvs with pixelwise depth， normal， and visibility, 6138-6147(10).

[77] J Y YANG, J M ALVAREZ, M M LIU. Non-parametric depth distribution modelling based depth inference for multi-view stereo, 8616-8624(18).

[78] S Q WANG, B LI, Y C DAI. Efficient multi-view stereo by iterative dynamic cost volume, 8645-8654(18).

[79] Y LI, Z ZHAO, J FAN et al. ADR-MVSNet： a cascade network for 3D point cloud reconstruction with pixel occlusion. Pattern Recognition, 125, 108516(2022).

[80] J LAFFERTY, A MCCALLUM, FC PEREIRA. Conditional random fields： probabilistic models for segmenting and labeling sequence data(2001).

[81] S ZHENG, S JAYASUMANA, B ROMERA-PAREDES et al. Conditional random fields as recurrent neural networks, 1529-1537(7).

[82] P KNÖBELREITER, C SORMANN, A SHEKHOVTSOV et al. Belief propagation reloaded： learning BP-Layers for labeling problems, 7897-7906(13).

[83] K Y LUO, T GUAN, L L JU et al. Attention-aware multi-view stereo, 1587-1596(13).

[84] Z Z WEI, Q T ZHU, C MIN et al. Bidirectional hybrid LSTM based recurrent neural network for multi-view stereo. IEEE Transactions on Visualization and Computer Graphics(2022).

[85] T Y LIN, P GOYAL, R GIRSHICK et al. Focal loss for dense object detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 42, 318-327(2020).

[86] H Z ZHOU, H L ZHAO, Q WANG et al. Miper-MVS： multi-scale iterative probability estimation with refinement for efficient multi-view stereo. Neural Networks, 162, 502-515(2023).

[87] Y K DING, Z Y LI, D H HUANG et al. Enhancing Multi-View stereo with contrastive matching and weighted focal loss, 821-825(2022).

[88] N IBRAHIMLI, H LEDOUX, J KOOIJ et al. DDL-MVS： Depth Discontinuity Learning for MVS Networks. arXiv, 2203-01391(2022). https：//arxiv.org/abs/2203.01391

[89] T KHOT, S AGRAWAL, S TULSIANI et al. Learning unsupervised multi-view stereopsis via robust photometric consistency. arXiv preprint arXiv：, 02706, 2019(1905).

[90] Y C DAI, Z D ZHU, Z B RAO et al. MVS2： Deep unsupervised multi-view stereo with multi-view symmetry, 1-8(2019).

[91] A MALLICK, J STÜCKLER, H LENSCH. Learning to adapt multi-view stereo by self-supervision. arXiv preprint arXiv, 2020.

[92] C FINN, P ABBEEL, S LEVINE. Model-agnostic meta-learning for fast adaptation of deep networks, 1126-1135(11).

[93] B C HUANG, H W YI, C HUANG et al. M3VSNET： unsupervised multi-metric multi-view stereo network, 3163-3167(19).

[94] H B XU, Z P ZHOU, Y QIAO et al. Self-supervised multi-view stereo via effective co-segmentation and data-augmentation. Proceedings of the AAAI Conference on Artificial Intelligence, 35, 3030-3038(2021).

[95] J Y YANG, J M ALVAREZ, M M LIU. Self-supervised learning of depth inference for multi-view stereo, 7522-7530(20).

[96] H B XU, Z P ZHOU, Y L WANG et al. Digging into uncertainty in self-supervised multi-view stereo, 6058-6067(10).

[97] S QI, X SANG, B YAN et al. Unsupervised multi-view stereo network based on multi-stage depth estimation. Image and Vision Computing, 122, 104449(2022).

[98] H DONG, J YAO. PatchMVSNet： patch-wise unsuper-vised multi-view stereo for weakly-textured surface reconstruction. arXiv preprint arXiv：, 2022.

[99] D CHANG, A BOŽIČ, T ZHANG et al. RC-MVSNet： Unsupervised Multi-View Stereo with Neural Rendering. Lecture Notes in Computer Science, 665-680(2022).

[100] B MILDENHALL, P P SRINIVASAN, M TANCIK et al. NeRF. Communications of the ACM, 65, 99-106(2022).

[101] A P CHEN, Z X XU, F Q ZHAO et al. MVSNeRF： fast generalizable radiance field reconstruction from multi-view stereo, 14104-14113(10).

[102] Q G XU, Z X XU, J PHILIP et al. Point-nerf： point-based neural radiance fields, 5428-5438(18).

[103] J Z ZHANG, M Q JI, G Y WANG et al. SurRF： unsupervised multi-view stereopsis by learning surface radiance field. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44, 7912-7927(2022).

[104] G HINTON, O VINYALS, J DEAN. Distilling the Knowledge in a Neural Network. arXiv, 1503-02531(2015). https：//arxiv.org/abs/1503.02531

[105] Y K DING, Q T ZHU, X Y LIU et al. KD-MVS： Knowledge Distillation Based Self-Supervised Learning for Multi-View Stereo. Lecture Notes in Computer Science, 630-646(2022).

[106] KOLTUN VLADLEN et al. Adaptive surface reconstruction with multiscale convolutional kernels. 2021 IEEE/CVF International Conference on Computer Vision (ICCV): 5631(5640).

[107] T SCHÖPS, T SATTLER, M POLLEFEYS. BAD SLAM： bundle adjusted direct RGB-D SLAM, 134-144(15).

[108] Y YAO, Z X LUO, S W LI et al. BlendedMVS： a large-scale dataset for generalized multi-view stereo networks, 1787-1796(13).

[109] J N ZHANG, J Z ZHANG, S MAO et al. GigaMVS： a benchmark for ultra-large-scale gigapixel-level 3D reconstruction. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44, 7534-7550(2022).

[110] Z Y MA, Z TEED, J DENG. Multiview Stereo with Cascaded Epipolar RAFT. Lecture Notes in Computer Science, 734-750(2022).

[111] Z X LI, W M ZUO, Z Q WANG et al. Confidence-based large-scale dense multi-view stereo. IEEE Transactions on Image Processing, 29, 7176-7191(2020).

[112] W LI, D ZHU, Q WANG. A single view leaf reconstruction method based on the fusion of ResNet and differentiable render in plant growth digital twin system. Computers and Electronics in Agriculture, 193, 106712(2022).

[113] X P DENG, S QIU, W Q JIN et al. Three-dimensional reconstruction method for bionic compound-eye system based on MVSNet network. Electronics, 11, 1790(2022).

[114] [114] 114郝雯， 张雯静， 梁玮， 等. 面向三维点云的场景识别方法综述［J］. 光学 精密工程， 2022， 30（16）： 1988-2005. doi: 10.37188/OPE.20223016.1988HAOW， ZHANGW J， LIANGW， et al. Scene recognition for 3D point clouds： a review［J］. Opt. Precision Eng.， 2022， 30（16）： 1988-2005. （in Chinese）. doi: 10.37188/OPE.20223016.1988

[115] T EBNER, I FELDMANN, S RENAULT et al. Multi-view reconstruction of dynamic real-world objects and their integration in augmented and virtual reality applications. Journal of the Society for Information Display, 25, 151-157(2017).

[116] [116] 116李兆歆， 蒋浩， 刘衍青， 等. 丝路文化虚拟体验中的多视角立体重建技术研究［J］. 计算机学报， 2022， 45（3）： 500-512. doi: 10.11897/SP.J.1016.2022.00500LIZ X， JIANGH， LIUY Q， et al. Research on multi-view stereo 3D reconstruction in virtual reality system of silk road cultural inheritance［J］. Chinese Journal of Computers， 2022， 45（3）： 500-512. （in Chinese）. doi: 10.11897/SP.J.1016.2022.00500

[117] [117] 117余加勇， 薛现凯， 陈昌富， 等. 基于无人机倾斜摄影的公路边坡三维重建与灾害识别方法［J］. 中国公路学报， 2022， 35（4）： 77-86. doi: 10.3969/j.issn.1001-7372.2022.04.005YUJ Y， XUEX K， CHENC F， et al. Three-dimensional reconstruction and disaster identification of highway slope using unmanned aerial vehicle-based oblique photography technique［J］. China Journal of Highway and Transport， 2022， 35（4）： 77-86. （in Chinese）. doi: 10.3969/j.issn.1001-7372.2022.04.005

[118] Z HU, Y HOU, P TAO et al. IMGTR： Image-triangle based multi-view 3D reconstruction for urban scenes. ISPRS Journal of Photogrammetry and Remote Sensing, 181, 191-204(2021).

[119] M ORSINGHER, P ZANI, P MEDICI et al. Revisiting patchmatch multi-view stereo for urban 3D reconstruction, 190-196(4).

[120] Y X ZHOU, R L EIMEN, E J SEIBEL et al. Cost-efficient video synthesis and evaluation for development of virtual 3D endoscopy. IEEE Journal of Translational Engineering in Health and Medicine, 9, 1-11(2021).

[121] [121] 121何东健， 熊虹婷， 芦忠忠， 等. 基于多视角立体视觉的拔节期玉米水分胁迫预测模型［J］. 农业机械学报， 2020， 51（6）： 248-257. doi: 10.6041/j.issn.1000-1298.2020.06.026HED J， XIONGH T， LUZ Z， et al. Predictive model of maize moisture stress during jointing stage based on multi-view stereo vision［J］. Transactions of the Chinese Society for Agricultural Machinery， 2020， 51（6）： 248-257. （in Chinese）. doi: 10.6041/j.issn.1000-1298.2020.06.026

[122] [122] 122王思启， 张家强， 李丽圆， 等. MVSNet在空间目标三维重建中的应用［J］. 中国激光， 2022， 49（23）： 2310003.WANGS Q， ZHANGJ Q， LIL Y， et al. Application of MVSNet in 3D reconstruction of space objects［J］. Chinese Journal of Lasers， 2022， 49（23）： 2310003. （in Chinese）

[123] A GÓMEZ, G RANDALL, G FACCIOLO et al. An Experimental comparison of multi-view stereo approaches on satellite images, 707-716(3).

[124] J C LU, Y X LI, Z C ZUO. SatMVS： A Novel 3D Reconstruction Pipeline for Remote Sensing Satellite Imagery. Lecture Notes in Electrical Engineering, 521-538(2022).