[1] [1] JARITZ M, DE ETTE R, WIRBEL E, et al. Sparse dense data with CNNs: depth completion semantic segmentation[C]International Conference on 3D Vision (3DV). Verona: IEEE, 2018: 52 60.

[2] SONG Z B, LU J F, YAO Y Z, et al. Self-supervised depth completion from direct visual-LiDAR odometry in autonomous driving[J]. IEEE Transactions on Intelligent Transportation Systems, 23, 11654-11665(2022).

[3] [3] DU R F, TURNER E, DZITSIUK M, et al. DepthLab: realtime 3D interaction with depth maps f mobile augmented reality[C]Proceedings of the 33rd Annual ACM Symposium on User Interface Software Technology. ACM, 2020: 829 − 843.

[4] MA F C, CARLONE L, AYAZ U, et al. Sparse depth sensing for resource-constrained robots[J]. The International Journal of Robotics Research, 38, 935-980(2019).

[5] TEIXEIRA L, OSWALD M R, POLLEFEYS M, et al. Aerial single-view depth completion with image-guided uncertainty estimation[J]. IEEE Robotics and Automation Letters, 5, 1055-1062(2020).

[6] [6] CHEN L, LIN H, LI S T. Depth image enhancement f Kinect using region growing bilateral filter[C]Proceedings of the 21st International Conference on Pattern Recognition. Tsukuba: IEEE, 2012: 3070 3073.

[7] [7] LIU S J, LAI P L, TIAN D, et al. Joint trilateral filtering f depth map compression[C]Proceedings of SPIE 7744, Visual Communications Image Processing 2010. Huangshan: SPIE, 2010: 77440F.

[8] [8] ALHWARIN F, FERREIN A, SCHOLL I. IR stereo Kinect: improving depth images by combining structured light with IR stereo[C]13th Pacific Rim International Conference on Artificial Intelligence. Gold Coast: Springer, 2014: 409 421.

[9] [9] CHIU W W C, BLANKE U, FRITZ M. Improving the Kinect by crossmodal stereo[C]British Machine Vision Conference. Dundee: BMVC, 2011: 1 10.

[10] CHEN K, LAI Y K, WU Y X, et al. Automatic semantic modeling of indoor scenes from low-quality RGB-D data using contextual information[J]. ACM Transactions on Graphics, 33, 208(2014).

[11] [11] ZHANG Y D, FUNKHOUSER T. Deep depth completion of a single RGBD image[C]Proceedings of the 2018 IEEECVF Conference on Computer Vision Pattern Recognition. Salt Lake City: IEEE, 2018: 175 185.

[12] [12] QIU J X, CUI Z P, ZHANG Y D, et al. DeepLiDAR: Deep surface nmal guided depth prediction f outdo scene from sparse LiDAR data single col image[C]Proceedings of the IEEECVF Conference on Computer Vision Pattern Recognition. Long Beach: IEEE, 2019: 3308 3317.

[13] [13] MA F C, CAVALHEIRO G V, KARAMAN S. Selfsupervised sparsetodense: selfsupervised depth completion from LiDAR monocular camera[C]2019 International Conference on Robotics Automation (ICRA). Montreal: IEEE, 2019: 3288 3295.

[14] ELDESOKEY A, FELSBERG M, KHAN F S. Confidence propagation through CNNs for guided sparse depth regression[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 42, 2423-2436(2020).

[15] [15] CHENG X J, WANG P, YANG R G. Depth estimation via affinity learned with convolutional spatial propagation wk[C]Proceedings of the 15th European Conference on Computer Vision (ECCV). Munich: Springer, 2018: 108 125.

[16] [16] HUANG Y K, WU T H, LIU Y C, et al. Indo depth completion with boundary consistency selfattention[C]Proceedings of the IEEECVF International Conference on Computer Vision Wkshop. Seoul: IEEE, 2019: 1070 1078.

[17] [17] SAJJAN S, MOE M, PAN M, et al. Clear grasp: 3D shape estimation of transparent objects f manipulation[C]2020 IEEE International Conference on Robotics Automation (ICRA). Paris: IEEE, 2020: 3634 3642.

[18] [18] ZHU L Y, MOUSAVIAN A, XIANG Y, et al. RGBD local implicit function f depth completion of transparent objects[C]Proceedings of the IEEECVF Conference on Computer Vision Pattern Recognition. Nashville: IEEE, 2021: 4647 4656.

[19] [19] HU M, WANG S L, LI B, et al. PE: towards precise efficient image guided depth completion[C]2021 IEEE International Conference on Robotics Automation (ICRA). Xi''an: IEEE, 2021: 13656 13662.

[20] [20] TANG Y J, CHEN J H, YANG Z G, et al. DepthGrasp: depth completion of transparent objects using selfattentive adversarial wk with spectral residual f grasping[C]2021 IEEERSJ International Conference on Intelligent Robots Systems (IROS). Prague: IEEE, 2021: 5710 5716.

[21] [21] MIYATO T, KATAOKA T, KOYAMA M, et al. Spectral nmalization f generative adversarial wks[C]6th International Conference on Learning Representations. Vancouver: ICLR, 2018.

[22] [22] WOO S, PARK J, LEE J Y, et al. CBAM: convolutional block attention module[C]Proceedings of the 15th European Conference on Computer Vision (ECCV). Munich: Springer, 2018: 3 19.

[23] FANG H J, FANG H S, XU S, et al. TransCG: a large-scale real-world dataset for transparent object depth completion and a grasping baseline[J]. IEEE Robotics and Automation Letters, 7, 7383-7390(2022).

[24] [24] PASZKE A, GROSS S, MASSA F, et al. PyTch: an imperative style, highperfmance deep learning library[C]Proceedings of the 33rd International Conference on Neural Infmation Processing Systems. Vancouver: NeurIPS, 2019: 721.

[25] [25] KINGMA D P, BA J. Adam: a method f stochastic optimization[C]3rd International Conference on Learning Representations. San Diego: ICLR, 2014.

[26] [26] SILBERMAN N, HOIEM D, KOHLI P, et al. Indo segmentation suppt inference from RGBD images[C]12th European Conference on Computer Vision. Flence: Springer, 2012: 746 760.

[27] [27] HARRISON A, NEWMAN P. Image sparse laser fusion f dense scene reconstruction[C]7th International Conference on Field Service Robotics. Cambridge: Springer, 2010: 219 228.

[28] [28] LIU J Y, GONG X J. Guided depth enhancement via anisotropic diffusion[C]14th PacificRim Conference on Advances in Multimedia Infmation Processing. Nanjing: Springer, 2013: 408 417.

[29] [29] SENUSHKIN D, ROMANOV M, BELIKOV I, et al. Decoder modulation f indo depth completion[C]2021 IEEERSJ International Conference on Intelligent Robots Systems (IROS). Prague: IEEE, 2021: 2181 2188.

[30] ALHASHIM I, WONKA P. High quality monocular depth estimation via transfer learning[J]. arXiv:, 11941, 2018(1812).