On the Importance of Stereo for Accurate Depth Estimation: An Efficient Semi-Supervised Deep Neural Network Approach
Open accessAbstract
We revisit the problem of visual depth estimation in the context of autonomous vehicles. Despite the progress on monocular depth estimation in recent years, we show that the gap between monocular and stereo depth accuracy remains large-a particularly relevant result due to the prevalent reliance upon monocular cameras by vehicles that are expected to be self-driving. We argue that the challenges of removing this gap are significant, owing to fundamental limitations of monocular vision. As a result, we focus our efforts on depth estimation by stereo. We propose a novel semi-supervised learning approach to training a deep stereo neural network, along with a novel architecture containing a machine-learned argmax layer and a custom runtime that enables a smaller version of our stereo DNN to run on an embedded GPU. Competitive results are shown on the KITTI 2015 stereo dataset. We also evaluate the recent progress of stereo algorithms by measuring the impact upon accuracy of various design criteria1.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The online error correction modules increase VIO robustness to spatial misalignments between camera and IMU that affect state-of-the-art traditional VIO methods.
“Additionally, we show how the OEC modules provide increased VIO robustness against spatial misalignments between a camera and IMU that plague SoA traditional approaches to VIO [3], [4], [5].”
From Unsupervised Deep Visual-Inertial Odometry with Online Error Correction for RGB-D Imagery (2020) · cites this paper as [5]
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 · see citing works
Image quality assessment: from error visibility to structural similarity
Wang, Z., Bovik, A. C., Sheikh, H. R., & Simoncelli, E. P. (2004) · IEEE Transactions on Image Processing · doi:10.1109/tip.2003.819861 · Cited by 57,892 · see citing works
Vision meets robotics: The KITTI dataset
Geiger, A., Lenz, P., Stiller, C., & Urtasun, R. (2013) · The International Journal of Robotics Research · doi:10.1177/0278364913491297 · Cited by 9,913 · see citing works
Jaderberg, M., Simonyan, K., Zisserman, A., & Kavukcuoglu, K. (2015) · arXiv · doi:10.48550/arxiv.1506.02025 · Cited by 5,137 · see citing works
Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)
Clevert, D.-A., Unterthiner, T., & Hochreiter, S. (2015) · arXiv · doi:10.48550/arxiv.1511.07289 · Cited by 4,513 · see citing works
Depth Map Prediction from a Single Image using a Multi-Scale Deep Network
Eigen, D., Puhrsch, C., & Fergus, R. (2014) · arXiv · doi:10.48550/arxiv.1406.2283 · Cited by 3,442 · see citing works
Unsupervised Monocular Depth Estimation with Left-Right Consistency
Godard, C., Aodha, O. M., & Brostow, G. J. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.699 · Cited by 3,270 · see citing works
Convergence Results for Neural Networks via Electrodynamics
Panigrahy, R., Rahimi, A., Sachdeva, S., et al. (2018) · Leibniz international proceedings in informatics · doi:10.4230/lipics.itcs.2018.22 · Cited by 2,848 · see citing works
Loss Functions for Image Restoration With Neural Networks
Zhao, H., Gallo, O., Frosio, I., & Kautz, J. (2016) · IEEE Transactions on Computational Imaging · doi:10.1109/tci.2016.2644865 · Cited by 2,659 · see citing works
Mayer, N., Ilg, E., Hausser, P., Fischer, P., Cremers, D., Dosovitskiy, A., & Brox, T. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.438 · Cited by 2,488 · see citing works
Unsupervised CNN for Single View Depth Estimation: Geometry to the Rescue
Garg, R., B.G., V. K., Carneiro, G., & Reid, I. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46484-8_45 · Cited by 1,632 · see citing works
End-to-End Learning of Geometry and Context for Deep Stereo Regression
Kendall, A., Martirosyan, H., Dasgupta, S., Henry, P., Kennedy, R., Bachrach, A., & Bry, A. (2017) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.17 · Cited by 1,531 · see citing works
Learning Depth from Single Monocular Images Using Deep Convolutional Neural Fields
Liu, F., Shen, C., Lin, G., & Reid, I. D. (2015) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2015.2505283 · Cited by 1,231 · see citing works
Stereo Matching by Training a Convolutional Neural Network to Compare Image PatchesPreprint
ŽbontarJure, & LeCunYann (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1510.05970 · Cited by 1,009 · see citing works
Semi-Supervised Deep Learning for Monocular Depth Map Prediction
Kuznietsov, Y., Stuckler, J., & Leibe, B. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.238 · Cited by 680 · see citing works
Ridley, H. (1973) · BMJ · doi:10.1136/bmj.4.5893.682-b · Cited by 538 · see citing works
Cascade Residual Learning: A Two-Stage Convolutional Neural Network for Stereo Matching
Pang, J., Sun, W., Ren, J., Yang, C., & Yan, Q. (2017) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw.2017.108 · Cited by 499 · see citing works
Rainbow Color Map (Still) Considered Harmful
Borland, D., & Taylor, R. M. (2007) · IEEE Computer Graphics and Applications · doi:10.1109/mcg.2007.323435 · Cited by 488 · see citing works
SGM-Nets: Semi-Global Matching with Neural Networks
Seki, A., & Pollefeys, M. (2017) · 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.2017.703 · Cited by 280 · see citing works
Displets: Resolving stereo ambiguities using object knowledge
Güney, F., & Geiger, A. (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.2015.7299044 · Cited by 217 · see citing works
Patch Based Confidence Prediction for Dense Disparity Map
Seki, A., & Pollefeys, M. (2016) · British Machine Vision Conference (BMVC) · doi:10.5244/c.30.23 · Cited by 153 · see citing works
Self-Supervised Learning for Stereo Matching with Self-Improving AbilityPreprint
Zhong, Y., Dai, Y., & Li, H. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1709.00930 · Cited by 134 · see citing works
Detect, Replace, Refine: Deep Structured Prediction for Pixel Wise Labeling
Gidaris, S., & Nikos Komodakis, A. (2017) · 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.2017.760 · Cited by 131 · see citing works
Binocular depth discrimination and estimation beyond interaction space
Allison, R. S., Gillam, B., & Vecellio, E. (2009) · Journal of Vision · doi:10.1167/9.1.10 · Cited by 104 · see citing works
Visual angle as a determinant of perceived interobject distance
Levin, C. A., & Haber, R. N. (1993) · Perception & Psychophysics · doi:10.3758/bf03211761 · Cited by 97 · see citing works
Stereoscopic perception of real depths at large distances
Palmisano, S. A., Gillam, B., Govan, D. G., Allison, R. S., & Harris, J. M. (2010) · Journal of Vision · doi:10.1167/10.6.19 · Cited by 97 · see citing works
Stereoscopic depth perception at far viewing distances
Cormack, R. H. (1984) · Perception & Psychophysics · doi:10.3758/bf03203918 · Cited by 43 · see citing works
Magnitude, precision, and realism of depth perception in stereoscopic vision
Hibbard, P. B., Haines, A. E., & Hornsey, R. L. (2017) · Cognitive Research Principles and Implications · doi:10.1186/s41235-017-0062-7 · Cited by 41 · see citing works
Learning Deep Correspondence through Prior and Posterior Feature ConstancyPreprint
Liang, Z., Feng, Y., Guo, Y., Liu, H., Qiao, L., Chen, W., Zhou, L. P., & Zhang, J. (2017) · arXiv (Cornell University) · Cited by 24 · see citing works
Flagged first, then by citations
2 of the 31 references couldn’t be matched to a known paper.
Cited by
Sorted by citations
Anytime Stereo Image Depth Estimation on Mobile Devices
Wang, Y., Lai, Z., Huang, G. M., Wang, B. H., van der Maaten, L., Campbell, M., & Weinberger, K. Q. (2019) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2019.8794003 · Cited by 219 · see citing works
Identification of Road-Surface Type Using Deep Neural Networks for Friction Coefficient Estimation
Šabanovič, E., Žuraulis, V., Prentkovskis, O., & Skrickij, V. (2020) · Sensors · doi:10.3390/s20030612 · Cited by 158 · see citing works
DIODE: A Dense Indoor and Outdoor DEpth DatasetPreprint
Vasiljevic, I., Kolkin, N., Zhang, S., Luo, R., Wang, H., Dai, F. Z., Daniele, A. F., Mostajabi, M., Basart, S., Walter, M. R., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1908.00463 · Cited by 169 · see citing works
Stereo Matching Using Multi-Level Cost Volume and Multi-Scale Feature Constancy
Liang, Z., Guo, Y., Feng, Y., Chen, W. R., Qiao, L., Zhou, L., Zhang, J., & Liu, H. (2019) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2019.2928550 · Cited by 123 · see citing works
Monocular Depth Estimation: A Thorough Review
Arampatzakis, V., Pavlidis, G., Mitianoudis, N., & Papamarkos, N. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2023.3330944 · Cited by 125 · see citing works
Khan, A., Ilyas, T., Umraiz, M., Mannan, Z. I., & Kim, H. (2020) · Electronics · doi:10.3390/electronics9101602 · Cited by 105 · see citing works
Stereo matching algorithm based on deep learning: A survey
Hamid, M. S., Manap, N. B. A., Hamzah, R. A., & Kadmin, A. F. (2020) · Journal of King Saud University - Computer and Information Sciences · doi:10.1016/j.jksuci.2020.08.011 · Cited by 103 · see citing works
PVStereo: Pyramid Voting Module for End-to-End Self-Supervised Stereo Matching
Wang, H., Fan, R., Cai, P., & Liu, M. (2021) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2021.3068108 · Cited by 89 · see citing works
Simulation-based lidar super-resolution for ground vehicles
Shan, T., Wang, J., Chen, F., Szenher, P., & Englot, B. (2020) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2020.103647 · Cited by 90 · see citing works
Focus on Defocus: Bridging the Synthetic to Real Domain Gap for Depth Estimation
Maximov, M., Galim, K., & Leal-Taixé, L. (2020) · 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/cvpr42600.2020.00115 · Cited by 86 · see citing works
Unsupervised Deep Visual-Inertial Odometry with Online Error Correction for RGB-D Imagery
Shamwell, E. J., Lindgren, K., Leung, S., & Nothwang, W. D. (2020) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2019.2909895 · Cited by 86 · see citing works
Low-cost SPAD sensing for non-line-of-sight tracking, material classification and depth imaging
Callenberg, C., Shi, Z., Heide, F., & Hullin, M. B. (2021) · ACM Transactions on Graphics · doi:10.1145/3450626.3459824 · Cited by 56 · see citing works
Pano Popups: Indoor 3D Reconstruction with a Plane-Aware Network
Eder, M., Moulon, P., & Guan, L. (2019) · International Conference on 3D Vision (3DV) · doi:10.1109/3dv.2019.00018 · Cited by 54 · see citing works
Autonomous Navigation of mobile robots in factory environment
Harapanahalli, S., O’Mahony, N., Velasco-Hernandez, G., Campbell, S., Riordan, D., & Walsh, J. L. (2019) · Procedia Manufacturing · doi:10.1016/j.promfg.2020.01.134 · Cited by 54 · see citing works
Reversing the Cycle: Self-supervised Deep Stereo Through Enhanced Monocular Distillation
Aleotti, F., Tosi, F., Zhang, L., Poggi, M., & Mattoccia, S. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-58621-8_36 · Cited by 50 · see citing works
An Alternative of LiDAR in Nighttime: Unsupervised Depth Estimation Based on Single Thermal Image
Lu, Y., & Lu, G. (2021) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv48630.2021.00388 · Cited by 49 · see citing works
A survey on conventional and learning‐based methods for multi‐view stereo
Stathopoulou, E. K., & Fabio Remondino, A. (2023) · The Photogrammetric Record · doi:10.1111/phor.12456 · Cited by 53 · see citing works
LiStereo: Generate Dense Depth Maps from LIDAR and Stereo Imagery
Zhang, J., Ramanagopal, M. S., Vasudevan, R., & Johnson‐Roberson, M. (2020) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra40945.2020.9196628 · Cited by 42 · see citing works
Mansour, M., Davidson, P., Степанов, О. А., & Piché, R. (2019) · Remote Sensing · doi:10.3390/rs11171990 · Cited by 38 · see citing works
SteReFo: Efficient Image Refocusing with Stereo Vision
Busam, B., Hog, M., McDonagh, S., & Slabaugh, G. (2019) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw.2019.00411 · Cited by 36 · see citing works
Monitoring Critical Infrastructure Using 3D LiDAR Point Clouds
Sharifisoraki, Z., Dey, A., Selzler, R., Amini, M., Green, J. R., Rajan, S., & Kwamena, F. (2022) · IEEE Access · doi:10.1109/access.2022.3232338 · Cited by 35 · see citing works
The Temporal Opportunist: Self-Supervised Multi-Frame Monocular Depth
Watson, J., Aodha, O. M., Prisacariu, V. A., Brostow, G., & Firman, M. (2021) · 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/cvpr46437.2021.00122 · Cited by 40 · see citing works
MultiDepth: Single-Image Depth Estimation via Multi-Task Regression and Classification
Liebel, L., & Körner, M. (2019) · IEEE International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc.2019.8917177 · Cited by 30 · see citing works
A Learned Stereo Depth System for Robotic Manipulation in Homes
Shankar, K., Tjersland, M., Ma, J., Stone, K., & Bajracharya, M. (2022) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2022.3143895 · Cited by 30 · see citing works
A Convolutional Attention Residual Network for Stereo Matching
Huang, G., Gong, Y., Xu, Q., Wattanachote, K., Zeng, K., & Luo, X. (2020) · IEEE Access · doi:10.1109/access.2020.2980243 · Cited by 29 · see citing works
A Survey of FPGA-Based Vision Systems for Autonomous Cars
Castells‐Rufas, D., Ngo, V., Borrego-Carazo, J., Codina, M., Sanchez, C., Gil, D., & Carrabina, J. (2022) · IEEE Access · doi:10.1109/access.2022.3230282 · Cited by 29 · see citing works
Light-weight network for real-time adaptive stereo depth estimation
Gan, W., Wong, P. K., Yu, G., Zhao, R., & Vong, C. (2021) · Neurocomputing · doi:10.1016/j.neucom.2021.02.014 · Cited by 24 · see citing works
Efficient stereo matching on embedded GPUs with zero-means cross correlation
Chang, Q., Zha, A., Wang, W., Liu, X., Onishi, M., Lei, L., Er, M. J., & Maruyama, T. (2021) · Journal of Systems Architecture · doi:10.1016/j.sysarc.2021.102366 · Cited by 22 · see citing works
Mask-ToF: Learning Microlens Masks for Flying Pixel Correction in Time-of-Flight Imaging
Chugunov, I., Baek, S., Fu, Q., Heidrich, W., & Heide, F. (2021) · 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/cvpr46437.2021.00900 · Cited by 20 · see citing works
Shi, H., Wang, Z., Zhou, Y., Li, D., Yang, X. Y., & Li, Q. (2023) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2023.3279899 · Cited by 18 · see citing works
TECHNOLOGICAL MEASURES OF FOREFRONT ROAD IDENTIFICATION FOR VEHICLE COMFORT AND SAFETY IMPROVEMENT
Žuraulis, V., Surblys, V., & Šabanovič, E. (2019) · Transport · doi:10.3846/transport.2019.10372 · Cited by 17 · see citing works
Computer Vision for 3D Perception
O’Mahony, N., Campbell, S., Krpálková, L., Riordan, D., Walsh, J. L., Murphy, A., & Ryan, C. (2018) · Advances in intelligent systems and computing · doi:10.1007/978-3-030-01057-7_59 · Cited by 16 · see citing works
PanoDepth: A Two-Stage Approach for Monocular Omnidirectional Depth Estimation
Li, Y., Yan, Z., Duan, Y., & Ren, L. (2021) · International Conference on 3D Vision (3DV) · doi:10.1109/3dv53792.2021.00074 · Cited by 16 · see citing works
Uncertainty depth estimation with gated images for 3D reconstruction
Walz, S., Gruber, T., Ritter, W., & Dietmayer, K. (2020) · IEEE International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc45102.2020.9294571 · Cited by 15 · see citing works
Driving Datasets Literature ReviewPreprint
Laflamme, C.-É. N., Pomerleau, F., & Giguère, P. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1910.11968 · Cited by 17 · see citing works
Tian, Y., Du, Y., Zhang, Q., Cheng, J. T., & Yang, Z. (2020) · IET Intelligent Transport Systems · doi:10.1049/iet-its.2019.0462 · Cited by 14 · see citing works
Real-time Vision Based Obstacle Detection in Maritime Environments
Nunes, D., Fortuna, J., Damas, B., & Ventura, R. (2022) · IEEE International Conference on Autonomous Robot Systems and Competitions · doi:10.1109/icarsc55462.2022.9784771 · Cited by 14 · see citing works
Pan, B., Jiao, J., Pang, J., & Cheng, J. S. (2024) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra57147.2024.10611085 · Cited by 13 · see citing works
Centimeter-wave Free-space Neural Time-of-Flight Imaging
Baek, S., Walsh, N., Chugunov, I., Shi, Z., & Heide, F. (2022) · ACM Transactions on Graphics · doi:10.1145/3522671 · Cited by 13 · see citing works
Fast CNN Stereo Depth Estimation through Embedded GPU Devices
Aguilera, C., Aguilera, C., Navarro, C. A., & Sappa, A. D. (2020) · Sensors · doi:10.3390/s20113249 · Cited by 13 · see citing works
StereoVAE: A lightweight stereo-matching system using embedded GPUs
Chang, Q., Li, X., Xu, X., Liu, X., Li, Y., & Miyazaki, J. (2023) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra48891.2023.10160441 · Cited by 12 · see citing works
Rao, Z., He, M., Dai, Y., & Shen, Z. (2020) · The Visual Computer · doi:10.1007/s00371-020-02001-5 · Cited by 12 · see citing works
MVSAnywhere: Zero-Shot Multi-View Stereo
Izquierdo, S., Sayed, M., Firman, M., Garcia-Hernando, G., Turmukhambetov, D., Civera, J., Aodha, O. M., Brostow, G., & Watson, J. (2025) · 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/cvpr52734.2025.01073 · Cited by 12 · see citing works
Domain-adaptive modules for stereo matching network
Ling, Z., Yang, K., Li, J., Zhang, Y., Gao, X., Luo, L., & Xie, L. (2021) · Neurocomputing · doi:10.1016/j.neucom.2021.06.004 · Cited by 11 · see citing works
Real‐time multi‐window stereo matching algorithm with fuzzy logic
Delgado, H. D. V., Pérez‐Patricio, M., Aguilar‐González, A., Arias-Estrada, M., Palacios-Ramos, M.-A., Camas‐Anzueto, J. L., Pérez-Cruz, A., & Velázquez-Trujillo, S. (2021) · IET Computer Vision · doi:10.1049/cvi2.12031 · Cited by 11 · see citing works
Optimized Convolutional Neural Network architecture for UAV navigation within unstructured trail
MENFOUKH, K., Touba, M. M., Khenfri, F., & Guettal, L. (2020) · International Conference on Communications, Control Systems and Signal Processing (CCSSP) · doi:10.1109/ccssp49278.2020.9151783 · Cited by 10 · see citing works
Hamid, M. S., Manap, N. B. A., Hamzah, R. A., & Kadmin, A. F. (2021) · International Journal of Emerging Technology and Advanced Engineering · doi:10.46338/ijetae0621_10 · Cited by 10 · see citing works
Soft Cross Entropy Loss and Bottleneck Tri-Cost Volume For Efficient Stereo Depth Prediction
Nuanes, T., Elsey, M., Sankaranarayanan, A. C., & Shen, J. P. (2021) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw53098.2021.00319 · Cited by 10 · see citing works
FastMDE: A Fast CNN Architecture for Monocular Depth Estimation at High Resolution
Dao, T.-T., Pham, Q., & Hwang, W. (2022) · IEEE Access · doi:10.1109/access.2022.3145969 · Cited by 9 · see citing works
Automatic testbed with a visual motion tracking system for airborne wind energy applications
Castro-Fernández, I., DeLosRíos-Navarrete, F., Borobia-Moreno, R., Fernández‐Jiménez, M., García‐Cousillas, H., Zas‐Bustingorri, M., Ghobaissi, A. T., López‐Vega, F., Best, K., Cavallaro, R., et al. (2023) · Wind Energy · doi:10.1002/we.2805 · Cited by 9 · see citing works
Displacement-Invariant Cost Computation for Stereo Matching
Zhong, Y., Loop, C., Byeon, W., Birchfield, S. T., Dai, Y., Zhang, K., Kamenev, A., Breuel, T. M., Li, H., & Kautz, J. (2022) · International Journal of Computer Vision · doi:10.1007/s11263-022-01595-8 · Cited by 9 · see citing works
Self-citationDeep Depth Fusion for Black, Transparent, Reflective and Texture-Less Objects
Chai, C.-Y., Wu, Y.-P., & Tsao, S. (2020) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra40945.2020.9196894 · Cited by 8 · see citing works
P3De - A Novel Pothole Detection Algorithm using 3D Depth Estimation
Das, S., & Kale, A. (2021) · International Conference for Emerging Technology (INCET) · doi:10.1109/incet51464.2021.9456343 · Cited by 7 · see citing works
TinyStereo: A Tiny Coarse-to-Fine Framework for Vision-Based Depth Estimation on Embedded GPUs
Chang, Q., Xu, X., Zha, A., Er, M. J., Sun, Y., & Li, Y. (2024) · IEEE Transactions on Systems Man and Cybernetics Systems · doi:10.1109/tsmc.2024.3395464 · Cited by 7 · see citing works
HawkDrive: A Transformer-driven Visual Perception System for Autonomous Driving in Night Scene
Guo, Z., Perminov, S., Konenkov, M., & Tsetserukou, D. (2024) · IEEE Intelligent Vehicles Symposium · doi:10.1109/iv55156.2024.10588447 · Cited by 7 · see citing works
The Depth Estimation Method Based on Double-Cues Fusion for Light Field Images
Liu, X., Fu, D., Wu, C., & Si, Z. (2019) · Lecture notes in electrical engineering · doi:10.1007/978-981-15-0474-7_67 · Cited by 7 · see citing works
Goutcher, R., Barrington, C., Hibbard, P. B., & Graham, B. P. (2021) · Journal of Vision · doi:10.1167/jov.21.7.13 · Cited by 7 · see citing works
Wietrzykowski, J., & Belter, D. (2022) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2022.3150841 · Cited by 7 · see citing works
Tian, X., He, Z., Zhang, Y., Liu, F., & Gu, T. (2025) · Sensors · doi:10.3390/s25206380 · Cited by 6 · see citing works
Depth by Poking: Learning to Estimate Depth from Self-Supervised Grasping
Goodrich, B., Kuefler, A., & Richards, W. D. (2020) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra40945.2020.9196797 · Cited by 6 · see citing works
Move to See Better: Towards Self-Supervised Amodal Object Detection.Preprint
Fang, Z., Jain, A., Sarch, G. H., Harley, A. W., & Fragkiadaki, K. (2020) · arXiv (Cornell University) · Cited by 6 · see citing works
Displacement-Invariant Cost Computation for Efficient Stereo MatchingPreprint
Zhong, Y., Loop, C., Byeon, W., Birchfield, S. T., Dai, Y., Zhang, K., Kamenev, A., Breuel, T. M., Li, H., & Kautz, J. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2012.00899 · Cited by 6 · see citing works
Self-citationEnergy-efficient Edge Approximation for Connected Vehicular Services
Katare, D., & Ding, A. Y. (2023) · Conference on Information Sciences and Systems · doi:10.1109/ciss56502.2023.10089724 · Cited by 5 · see citing works
Karimi, H., Dolati, A., & Layeghi, K. (2022) · Displays · doi:10.1016/j.displa.2022.102300 · Cited by 5 · see citing works
Chang, Q., Zha, A., Wang, W., Liu, X., Onishi, M., & Maruyama, T. (2020) · IEEE International Conference on Computer Design: VLSI in Computers and Processors (ICCD) · doi:10.1109/iccd50377.2020.00104 · Cited by 5 · see citing works
PlaneLoc2: Indoor Global Localization Using Planar Segments and Passive Stereo Camera
Wietrzykowski, J. (2022) · IEEE Access · doi:10.1109/access.2022.3185732 · Cited by 4 · see citing works
Using Monocular Depth Estimation for Distance Estimation in a Moving Vehicle
Guzman, L. B. N. D., & See, A. R. (2023) · International Conference on Computer Graphics and Image Processing (CGIP) · doi:10.1109/cgip58526.2023.00012 · Cited by 4 · see citing works
Liu, Y. (2020) · Sensors · doi:10.3390/s20071979 · Cited by 4 · see citing works
Ji, Z., Song, X., Song, H., Hong, Y., & Guo, X. (2021) · Neurocomputing · doi:10.1016/j.neucom.2021.05.089 · Cited by 4 · see citing works
Multi-Resolution Monocular Depth Map Fusion by Self-Supervised Gradient-Based Composition
Dai, Y., Yi, R., Zhu, C., He, H., & Xu, K. (2023) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v37i1.25123 · Cited by 3 · see citing works
Towards Robust Perception Depth Information For Collision Avoidance
Saleh, S. M., Manoharan, S., Nine, J., & Hardt, W. (2020) · IEEE Congreso Bienal de Argentina (ARGENCON) · doi:10.1109/argencon49523.2020.9505483 · Cited by 3 · see citing works
Context Geometry Volume and Warping Refinement for Real-Time Stereo Matching
Liu, N., Zhao, N., Ou, Y. D., Wu, Q., & Ouyang, X. (2025) · Electronics · doi:10.3390/electronics14050892 · Cited by 2 · see citing works
ARUNet: Advancing Real-Time Stereo Matching for Robotic Perception on Edge Devices
Liang, B., Wang, Y., Huang, Z., Hu, Z., Hu, H., Xu, J., & Chen, D. (2025) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2025.3589145 · Cited by 2 · see citing works
Energy-Constrained Deep Neural Network Compression for Depth Estimation
Zeng, X., Zhang, M., Zhong, Z., & Liu, Y. (2023) · Electronics · doi:10.3390/electronics12030732 · Cited by 2 · see citing works
PrimitivePose: 3D Bounding Box Prediction of Unseen Objects via Synthetic Geometric Primitives
Kriegler, A., Beleznai, C., Murschitz, M., Göbel, K., & Gelautz, M. (2022) · IEEE International Conference on Robotic Computing (IRC) · doi:10.1109/irc55401.2022.00040 · Cited by 2 · see citing works
The human in the loop Perspectives and challenges for RoboCup 2050
Rossi, A., Paetzel, M., Keijsers, M., Anderson, M., Anderson, S., Barry, D., Gutsche, J., Hart, J., Iocchi, L., Kokkelmans, A. A., et al. (2024) · Autonomous Robots · doi:10.1007/s10514-024-10159-3 · Cited by 2 · see citing works
SmartReview: A Blockchain-based Transaction Review System for Decentralized Marketplaces
Aljohani, M., Mukkamala, R., Olariu, S., Kalari, S., & Sunkara, M. (2024) · International Conference on Blockchain Computing and Applications (BCCA) · doi:10.1109/bcca62388.2024.10844485 · Cited by 2 · see citing works
MPDCompress - Matrix Permutation Decomposition Algorithm for Deep Neural Network CompressionPreprint
Supic, L., Naous, R., Sredojević, R., Faust, A., & Stojanovic, V. M. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1805.12085 · Cited by 2 · see citing works
CKDNet: A Cascaded Knowledge Distillation Framework for Lightweight Stereo Matching
Pan, B., Pang, J., & Cheng, J. S. (2024) · International Conference on Intelligent Computing and Human-Computer Interaction (ICHCI) · doi:10.1109/ichci63580.2024.10808024 · Cited by 1 · see citing works
PotholeSAM: Pothole Management Using Segment Anything Model 2
Choi, W., Na, S., Lee, Y., Kim, C.-K., & Heo, S. (2025) · Journal of the Computational Structural Engineering Institute of Korea · doi:10.7734/coseik.2025.38.3.139 · Cited by 1 · see citing works
Binocular Stereo Vision in Remote Sensing: A Review
Li, X., Zhou, H., Sun, M., Xiong, B., Dai, Y., He, R., Chen, Z., & Rao, Z. (2026) · Remote Sensing · doi:10.3390/rs18101480 · Cited by 1 · see citing works
Distill Any Depth: Distillation Creates a Stronger Monocular Depth Estimator
He, X., Guo, D., Li, H., Cui, Y., Weng, L., Li, R., & Zhang, C. (2026) · doi:10.1109/cvprf71909.2026.00061 · Cited by 1 · see citing works
Šabanovič, E. (2019) · doi:10.20334/2019-051-m · Cited by 1 · see citing works
Li, W., John, V., & Mita, S. (2021) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr48806.2021.9412461 · Cited by 1 · see citing works
CVE-Net: cost volume enhanced network guided by sparse features for stereo matching
Xu, Q., Liu, S., Huang, G., Zeng, K., Gong, Y., & Luo, X. (2021) · Soft Computing · doi:10.1007/s00500-021-06257-4 · Cited by 1 · see citing works
Adaptive View Sampling for Efficient Synthesis of 3D View Using Calibrated Array Cameras
Kim, G., & Lee, D. (2021) · Electronics · doi:10.3390/electronics10010082 · Cited by 1 · see citing works
Multiple Scale Aggregation with Patch Multiplexing for High-Speed Inter-Vehicle Distance Estimation
Hirano, M., Yamakawa, Y., Senoo, T., Kishi, N., & Ishikawa, M. (2021) · IEEE Intelligent Vehicles Symposium · doi:10.1109/iv48863.2021.9575418 · Cited by 1 · see citing works
See far with TPNET: a Tile Processor and a CNN SymbiosisPreprint
Filippov, A., & Dzhimiev, O. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1811.08032 · Cited by 1 · see citing works
A Hybrid mmWave and Camera System for Long-Range Depth ImagingPreprint
Prabhakara, A., Zhang, D., Li, C., Munir, S., Sankanaryanan, A., Rowe, A., & Kumar, S. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2106.07856 · Cited by 1 · see citing works
Depth Generation Network: Estimating Real World Depth from Stereo and Depth Images
Dong, Z., Gao, Y., Ren, Q., Yan, Y., & Chen, F. (2019) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2019.8794315
Research of road scene object detection algorithm based on mobile platform
Chen, Y., Liu, X., & Wang, C. (2020) · International Workshop on Pattern Recognition (IWPR) · doi:10.1117/12.2574416
Centimeter-Wave Free-Space Time-of-Flight ImagingPreprint
Baek, S., Walsh, N., Chugunov, I., Shi, Z., & Heide, F. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2105.11606
Learning of Monocular Camera Depth Estimation Using Point-of-view Shots
Yoo, B., Yim, S., Lee, W., Lee, G.-I., Kim, D., Kwon, T., & Jeong, J. (2021) · doi:10.1145/3459066.3459073
A Generative Model for the Creation of Large Synthetic Image Datasets Used for Distance Estimation
Nešić, N., Vidović, M., Radosavljević, I., Mitrović, A., & Obradović, Đ. (2021) · Studies in computational intelligence · doi:10.1007/978-3-030-72711-6_15
Unsupervised Learning for Stereo Depth Estimation using Efficient Correspondence Matching
Wenbin, H., & Kamata, S. (2021) · International Conference on Advances in Image Processing (ICAIP) · doi:10.1145/3502827.3502828
Deep Stereo Network With Cross-Correlation Volume Construction and Least Square Aggregation
An, G., Wang, Y., Mo, Y., Zeng, K., Zhu, Q. X., & Yuan, X. (2025) · IEEE Access · doi:10.1109/access.2025.3538762
Enhanced Depth Estimation for Stereo Images using SIFT Features
Madake, J., Kulkarni, M., Kothawade, A., & Lakhote, S. (2024) · International Conference on Sustainable Communication Networks and Application (ICSCNA) · doi:10.1109/icscna63714.2024.10864301
- Authors
- Smolyanskiy, N., Kamenev, A., & Birchfield, S.
- Affiliations
- Nvidia (United Kingdom) (GB)
- Venue
- 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
- Publisher
- IEEE
- Published
- 2018-06
- Pages
- 1120-11208
- OpenAlex
- W2795023265
- Cited by
- 104
- References
- 31
- Citations by year
- 2026: 3 · 2025: 6 · 2024: 7 · 2023: 9 · 2022: 14 · 2021: 25 · 2020: 21 · 2019: 16 · 2018: 3
- FWCI
- 4.82
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Vision and Imaging
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Engineering › Automotive Engineering › Autonomous Vehicle Technology and Safety
- Keywords
- stereo depth estimation, monocular depth estimation, semi-supervised learning, autonomous vehicles
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
