Deep Learning Based Monocular Depth Estimation: Survey
0
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
Monocular depth estimation helps the robot to understand the surrounding environments in 3D. Especially, deep-learningbased monocular depth estimation has been widely researched, because it may overcome the scale ambiguity problem, which is a main issue in classical methods. Those learning based methods can be mainly divided into three parts: supervised learning, unsupervised learning, and semi-supervised learning. Supervised learning trains the network from dense groundtruth depth information, unsupervised one trains it from images sequences and semi-supervised one trains it from stereo images and sparse ground-truth depth. We describe the basics of each method, and then explain the recent research efforts to enhance the depth estimation performance.
Abstract
Monocular depth estimation helps the robot to understand the surrounding environments in 3D. Especially, deep-learningbased monocular depth estimation has been widely researched, because it may overcome the scale ambiguity problem, which is a main issue in classical methods. Those learning based methods can be mainly divided into three parts: supervised learning, unsupervised learning, and semi-supervised learning. Supervised learning trains the network from dense groundtruth depth information, unsupervised one trains it from images sequences and semi-supervised one trains it from stereo images and sparse ground-truth depth. We describe the basics of each method, and then explain the recent research efforts to enhance the depth estimation performance.
참고문헌 (27)
- Aleotti, F., "Generative adversarial networks for unsupervised monocular depth prediction", Proceedings of the European Conference on Computer Vision Workshops, pp.337~354 (2018)
- Almalioglu, Y., "Ganvo: Unsupervised deep monocular visual odometry and depth estimation with generative adversarial networks", International Conference on Robotics and Automation, pp.5474~5480 (2019)
- Cordts, M., "The cityscapes dataset for semantic urban scene understanding", Proceedings of the IEEE conference on Computer Vision and Pattern Recognition, pp.3213~3223 (2016)
- Eigen, D., "Depth map prediction from a single image using a multi-scale deep network", Advances in Neural Information Processing Systems, pp.2366~2374 (2014)
- Forster, C., "SVO: Fast semi-direct monocular visual odometry", IEEE international conference on robotics and automation, pp.15~22 (2014)
- Fu, H., "Deep Ordinal Regression Network for Monocular Depth Estimation", Proceedings of the IEEE, 2018, 2002~2011
- Garg, R., "Unsupervised Cnn for Single View Depth Estimation: Geometry to the Rescue", European conference on computer vision, pp.740~756 (2016)
- Geiger, A., "Are we ready for autonomous driving? the kitti vision benchmark suite", Proceedings of the IEEE conference on Computer Vision and Pattern Recognition, pp.3354~3361 (2012)
- Godard, C., "Unsupervised Monocular Depth Estimation with Left-Right Consistency", Proceedings of the IEEE conference on Computer Vision and Pattern Recognition, pp.270~279 (2017)
- Godard, C., "Digging Into Self-Supervised Monocular Depth Estimation", Proceedings of the IEEE, 2019, 3828~3838
- He, K., "Deep Residual Learning for Image Recognition", Proceedings of the IEEE conference on Computer Vision and Pattern Recognition, pp.770~778 (2016)
- "Mobilenets: Efficient convolutional neural networks for mobile vision applications" (2017)[URL]
- "Advances in Neural Information Processing Systems" (2015)[URL]
- Kundu, J. N., "AdaDepth: Unsupervised Content Congruent Adaptation for Depth Estimation", Proceedings of the IEEE, 2018, 2656~2665
- Kuznietsov, Y., "Semi-Supervised Deep Learning for Monocular Depth Map Prediction", Proceedings of the IEEE conference on Computer Vision and Pattern Recognition, pp.6647~6655 (2017)
- Laina, I., "Deeper Depth Prediction with Fully Convolutional Residual Networks", Fourth International Conference on 3D Vision, pp.239~248 (2016)
- Lee, J., "Monocular Depth Estimation Using Relative Depth Maps", Proceedings of the IEEE, 2019, 9729~9738
- Raul Mur-Artal, "ORB-SLAM: A Versatile and Accurate Monocular SLAM System", IEEE Transactions on Robotics, 31(5), pp.1147~1163 (2015), Institute of Electrical and Electronics Engineers (IEEE)[DOI]
- Ranftl, R., "Dense Monocular Depth Estimation in Complex Dynamic Scenes", Proceedings of the IEEE conference on Computer Vision and Pattern Recognition, pp.4058~4066 (2016)
- Silberman, N., "Indoor Segmentation and Support Inference from RGBD Images", European Conference on Computer Vision, pp.746~760 (2012)
- Wang, R., "Recurrent Neural Network for (Un-)Supervised Learning of Monocular Video Visual Odometry and Depth", Proceedings of the IEEE, 2019, 5555~5564
- Wofk, D., "FastDepth: Fast Monocular Depth Estimation on Embedded Systems", International Conference on Robotics and Automation, pp.6101~6108 (2019)
- Yin, Z., "GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Pose", Proceedings of the IEEE, 2018, 1983~1992
- Zhao, S., "Geometry-Aware Symmetric Domain Adaptation for Monocular Depth Estimation", Proceedings of the IEEE, 2019, 9788~9798
- Zheng, C., "T2net: Synthetic-to- Realistic Translation for Solving Single-Image Depth Estimation Tasks", Proceedings of the European Conference on Computer Vision, pp.798~814 (2018)
- Zhou, T., "Unsupervised Learning of Depth and Ego-Motion from Video", Proceedings of the IEEE conference on Computer Vision and Pattern Recognition, pp.1851~1858 (2017)
- Zhu, J. Y., "Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks", Proceedings of the IEEE International Conference on Computer Vision, pp.2223~2232 (2017)