The DOI matches its Crossref record; 68 of the 68 references it cites were found in a registry or an index.
Learning Guided Convolutional Network for Depth Completion
Open accessAbstract
Dense depth perception is critical for autonomous driving and other robotics applications. However, modern LiDAR sensors only provide sparse depth measurement. It is thus necessary to complete the sparse LiDAR data, where a synchronized guidance RGB image is often used to facilitate this completion. Many neural networks have been designed for this task. However, they often naïvely fuse the LiDAR data and RGB image information by performing feature concatenation or element-wise addition. Inspired by the guided image filtering, we design a novel guided network to predict kernel weights from the guidance image. These predicted kernels are then applied to extract the depth image features. In this way, our network generates content-dependent and spatially-variant kernels for multi-modal feature fusion. Dynamically generated spatially-variant kernels could lead to prohibitive GPU memory consumption and computation overhead. We further design a convolution factorization to reduce computation and memory consumption. The GPU memory reduction makes it possible for feature fusion to work in multi-stage scheme. We conduct comprehensive experiments to verify our method on real-world outdoor, indoor and synthetic datasets. Our method produces strong results. It outperforms state-of-the-art methods on the NYUv2 dataset and ranks 1st on the KITTI depth completion benchmark at the time of submission. It also presents strong generalization capability under different 3D point densities, various lighting and weather conditions as well as cross-dataset evaluations. The code will be released for reproduction.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Ioffe, S., & Szegedy, C. (2015) · arXiv · doi:10.48550/arxiv.1502.03167 · Cited by 27,818
MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
Howard, A. G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., & Adam, H. (2017) · arXiv · doi:10.48550/arxiv.1704.04861 · Cited by 19,015
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Ioffe, S. (2024) · arXiv (Cornell University) · doi:10.57702/o9raffed · Cited by 14,214
Decoupled Weight Decay Regularization
Loshchilov, I., & Hutter, F. (2017) · arXiv · doi:10.48550/arxiv.1711.05101 · Cited by 12,522
Bilateral Filtering for Gray and Color Images
Tomasi, C., & Manduchi, R. (2002) · Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271) · doi:10.1109/iccv.1998.710815 · Cited by 8,177 · cited 2×
“Our work is inspired by the guided image filtering [13], [14].”
MethodDeformable Convolutional Networks
Dai, J., Qi, H., Xiong, Y., Li, Y., Zhang, G., Hu, H., & Wei, Y. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.89 · Cited by 7,513
Indoor segmentation and support inference from rgbd images
Silberman, N., Hoiem, D., Kohli, P., & Fergus, R. (2012) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-33715-4_54 · Cited by 5,760
He, K., Sun, J., & Tang, X. (2013) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2012.213 · Cited by 5,546
Stereo Processing by Semiglobal Matching and Mutual Information
Hirschmuller, H. (2008) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2007.1166 · Cited by 4,195
SUN RGB-D: A RGB-D scene understanding benchmark suite
Song, S., Lichtenberg, S. P., & Xiao, J. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298655 · Cited by 1,943
A Closed-Form Solution to Natural Image Matting
Levin, A., Lischinski, D., & Weiss, Y. (2008) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2007.1177 · Cited by 1,616
He, K., Sun, J., & Tang, X. (2010) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-15549-9_1 · Cited by 1,565
Context Encoding for Semantic Segmentation
Zhang, H., Dana, K., Shi, J., Zhang, Z., Wang, X., Tyagi, A., & Agrawal, A. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00747 · Cited by 1,464
Colorization using optimization
Levin, A., Lischinski, D., & Weiss, Y. (2004) · ACM Transactions on Graphics · doi:10.1145/1015706.1015780 · Cited by 1,411
Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphs
Simonovsky, M., & Komodakis, N. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.11 · Cited by 1,266
VirtualWorlds as Proxy for Multi-object Tracking Analysis
Gaidon, A., Wang, Q., Cabon, Y., & Vig, E. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.470 · Cited by 1,079
Uhrig, J., Schneider, N., Schneider, L., Franke, U., Brox, T., & Geiger, A. (2017) · 2017 International Conference on 3D Vision (3DV) · doi:10.1109/3dv.2017.00012 · Cited by 924
Kopf, J., Cohen, M. F., Lischinski, D., & Uyttendaele, M. (2007) · ACM SIGGRAPH 2007 papers · doi:10.1145/1275808.1276497 · Cited by 872
Kopf, J., Cohen, M. F., Lischinski, D., & Uyttendaele, M. (2007) · ACM Transactions on Graphics · doi:10.1145/1276377.1276497 · Cited by 845
SUN3D: A Database of Big Spaces Reconstructed Using SfM and Object Labels
Xiao, J., Owens, A., & Torralba, A. (2013) · 2013 IEEE International Conference on Computer Vision · doi:10.1109/iccv.2013.458 · Cited by 803
Deep bilateral learning for real-time image enhancement
Gharbi, M., Chen, J., Barron, J. T., Hasinoff, S. W., & Durand, F. (2017) · ACM Transactions on Graphics · doi:10.1145/3072959.3073592 · Cited by 800
Computing the stereo matching cost with a convolutional neural network
Zbontar, J., & LeCun, Y. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298767 · Cited by 796
Spatial-Depth Super Resolution for Range Images
Yang, Q., Yang, R., Davis, J., & Nister, D. (2007) · 2007 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2007.383211 · Cited by 745
Efficient Deep Learning for Stereo Matching
Luo, W., Schwing, A. G., & Urtasun, R. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.614 · Cited by 741
Evaluation of Stereo Matching Costs on Images with Radiometric Differences
Hirschmuller, H., & Scharstein, D. (2009) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2008.221 · Cited by 721
Sparse-to-Dense: Depth Prediction from Sparse Depth Samples and a Single Image
Ma, F., & Karaman, S. (2018) · 2018 IEEE International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra.2018.8460184 · Cited by 650
Zhang, Q., Shen, X., Xu, L., & Jia, J. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10578-9_53 · Cited by 580
Image Guided Depth Upsampling Using Anisotropic Total Generalized Variation
Ferstl, D., Reinbacher, C., Ranftl, R., Ruether, M., & Bischof, H. (2013) · 2013 IEEE International Conference on Computer Vision · doi:10.1109/iccv.2013.127 · Cited by 528
High quality depth map upsampling for 3D-TOF cameras
Park, J., Kim, H., Tai, Y.-W., Brown, M. S., & Kweon, I. (2011) · 2011 International Conference on Computer Vision · doi:10.1109/iccv.2011.6126423 · Cited by 510
Brabandere, B. D., Jia, X., Tuytelaars, T., & Gool, L. V. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1605.09673 · Cited by 461
Self-Supervised Sparse-to-Dense: Self-Supervised Depth Completion from LiDAR and Monocular Camera
Ma, F., Cavalheiro, G. V., & Karaman, S. (2019) · 2019 International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra.2019.8793637 · Cited by 460
Deep Depth Completion of a Single RGB-D Image
Zhang, Y., & Funkhouser, T. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00026 · Cited by 427
Qiu, J., Cui, Z., Zhang, Y., Zhang, X., Liu, S., Zeng, B., & Pollefeys, M. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00343 · Cited by 410
Depth Estimation via Affinity Learned with Convolutional Spatial Propagation Network
Cheng, X., Wang, P., & Yang, R. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01270-0_7 · Cited by 357
Learning Depth with Convolutional Spatial Propagation Network
Cheng, X., Wang, P., & Yang, R. (2018) · arXiv · doi:10.48550/arxiv.1810.02695 · Cited by 345 · cited 1×
“Totally, we evaluate our model on 3944 image frames, with ‘DDP’ [55], ‘DeepLiDAR’ [6], ‘CSPN’ [35], [56] and ‘NConv-CNN’ [33].”
Learning Depth with Convolutional Spatial Propagation Network
Cheng, X., Wang, P., & Yang, R. (2020) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2019.2947374 · Cited by 341
In Defense of Classical Image Processing: Fast Depth Completion on the CPU
Ku, J., Harakeh, A., & Waslander, S. L. (2018) · 2018 15th Conference on Computer and Robot Vision (CRV) · doi:10.1109/crv.2018.00013 · Cited by 325
Sparse and Dense Data with CNNs: Depth Completion and Semantic Segmentation
Jaritz, M., Charette, R. D., Wirbel, E., Perrotton, X., & Nashashibi, F. (2018) · 2018 International Conference on 3D Vision (3DV) · doi:10.1109/3dv.2018.00017 · Cited by 299
Fast End-to-End Trainable Guided Filter
Wu, H., Zheng, S., Zhang, J., & Huang, K. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00197 · Cited by 278
Li, Y., Huang, J.-B., Ahuja, N., & Yang, M.-H. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46493-0_10 · Cited by 269
Sparse and Noisy LiDAR Completion with RGB Guidance and Uncertainty
Van Gansbeke, W., Neven, D., De Brabandere, B., & Van Gool, L. (2019) · 2019 16th International Conference on Machine Vision Applications (MVA) · doi:10.23919/mva.2019.8757939 · Cited by 264
A Category-Level 3D Object Dataset: Putting the Kinect to Work
Janoch, A., Karayev, S., Jia, Y., Barron, J. T., Fritz, M., Saenko, K., & Darrell, T. (2013) · Advances in Computer Vision and Pattern Recognition · doi:10.1007/978-1-4471-4640-7_8 · Cited by 254
Depth Completion From Sparse LiDAR Data With Depth-Normal Constraints
Xu, Y., Zhu, X., Shi, J., Zhang, G., Bao, H., & Li, H. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00290 · Cited by 246
Cheng, X., Wang, P., Guan, C., & Yang, R. (2020) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v34i07.6635 · Cited by 245
Joint Geodesic Upsampling of Depth Images
Liu, M.-Y., Tuzel, O., & Taguchi, Y. (2013) · 2013 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2013.29 · Cited by 244
Confidence Propagation through CNNs for Guided Sparse Depth Regression
Eldesokey, A., Felsberg, M., & Khan, F. S. (2020) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2019.2929170 · Cited by 217
Patch Based Synthesis for Single Depth Image Super-Resolution
Mac Aodha, O., Campbell, N. D. F., Nair, A., & Brostow, G. J. (2012) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-33712-3_6 · Cited by 211
Edge-Guided Single Depth Image Super Resolution
Xie, J., Feris, R. S., & Sun, M.-T. (2016) · IEEE Transactions on Image Processing · doi:10.1109/tip.2015.2501749 · Cited by 198
Learning Joint 2D-3D Representations for Depth Completion
Chen, Y., Yang, B., Liang, M., & Urtasun, R. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.01012 · Cited by 177
HMS-Net: Hierarchical Multi-Scale Sparsity-Invariant Network for Sparse Depth Completion
Huang, Z., Fan, J., Cheng, S., Yi, S., Wang, X., & Li, H. (2020) · IEEE Transactions on Image Processing · doi:10.1109/tip.2019.2960589 · Cited by 160
A Multi-Scale Guided Cascade Hourglass Network for Depth Completion
Li, A., Yuan, Z., Ling, Y., Chi, W., Zhang, S., & Zhang, C. (2020) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv45572.2020.9093407 · Cited by 159
ATGV-Net: Accurate Depth Super-Resolution
Riegler, G., Rüther, M., & Bischof, H. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-46487-9_17 · Cited by 157
Robust image filtering using joint static and dynamic guidance
Ham, B., Cho, M., & Ponce, J. (2015) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2015.7299115 · Cited by 147
Dense Depth Posterior (DDP) From Single Image and Sparse Range
Yang, Y., Wong, A., & Soatto, S. (2019) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2019.00347 · Cited by 136
Deep Convolutional Compressed Sensing for LiDAR Depth Completion
Chodosh, N., Wang, C., & Lucey, S. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-20887-5_31 · Cited by 130
Cross-Field Joint Image Restoration via Scale Map
Yan, Q., Shen, X., Xu, L., et al. (2013) · IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2013.194 · Cited by 123
High-Quality Depth Map Upsampling and Completion for RGB-D Cameras
Park, J., Kim, H., Tai, Y., Brown, M. S., & Kweon, I. S. (2014) · IEEE Transactions on Image Processing · doi:10.1109/tip.2014.2361034 · Cited by 115
Mutual-Structure for Joint Filtering
Shen, X., Zhou, C., Li, X., et al. (2015) · IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.389 · Cited by 113
Joint Super Resolution and Denoising From a Single Depth Image
Xie, J., Feris, R., Yu, S.-S., & Sun, M. (2015) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2015.2457678 · Cited by 104
Dense disparity maps from sparse disparity measurements
Hawe, S., Kleinsteuber, M., & Diepold, K. J. (2011) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2011.6126488 · Cited by 103
Depth Reconstruction From Sparse Samples: Representation, Algorithm, and Sampling
Liu, L.-K., Chan, S. H., & Nguyen, T. Q. (2015) · IEEE Transactions on Image Processing · doi:10.1109/tip.2015.2409551 · Cited by 101
Depth Super Resolution by Rigid Body Self-Similarity in 3D
Hornáček, M., Rhemann, C., Gelautz, M., & Rother, C. (2013) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2013.149 · Cited by 99
Variational Depth Superresolution Using Example-Based Edge Representations
Ferstl, D., Rüther, M., & Bischof, H. (2015) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.66 · Cited by 88
Semantically Guided Depth Upsampling
Schneider, N., Schneider, L., Pinggera, P., Franke, U., Pollefeys, M., & Stiller, C. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-45886-1_4 · Cited by 88
Dynamic Filtering with Large Sampling Field for ConvNets
Wu, J., Dai, L., Yu, Y., Bajaj, C., & Ji, X. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-01249-6_12 · Cited by 50
Depth Completion with Deep Geometry and Context Guidance
Lee, B.-U., Jeon, H., Im, S., & Kweon, I. S. (2019) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2019.8794161 · Cited by 37
Cited by
Deep Learning for Image and Point Cloud Fusion in Autonomous Driving: A Review
Cui, Y., Chen, R., Chu, W., Chen, L., Tian, D., Li, Y., & Cao, D. (2022) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2020.3023541 · Cited by 550
PENet: Towards Precise and Efficient Image Guided Depth Completion
Hu, M., Wang, S., Li, B., Ning, S., Fan, L., & Gong, X. (2021) · 2021 IEEE International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra48506.2021.9561035 · Cited by 338
Learning Depth-Guided Convolutions for Monocular 3D Object Detection
Ding, M., Huo, Y., Yi, H., Wang, Z., Shi, J., Lu, Z., & Luo, P. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.01169 · Cited by 259
Metadata
- Authors
- Tang, J., Tian, F.-P., Feng, W., Li, J., & Tan, P.
- Venue
- IEEE Transactions on Image Processing
- Published
- 2021
- Volume
- 30
- Pages
- 1116-1129
- ISSN
- 1057-7149 (ISSN-L)
- 1941-0042
- OpenAlex
- W3110653837
- Cited by
- 291
- References
- 68
- FWCI
- 14.99
- Type
- journal article
- Language
- en
- Open access
- green
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.