基于数据增强的半监督单目深度估计框架

doi:10.13229/j.cnki.jdxbgxb.20230964

Abstract

Abstract:

To address the problem of requiring a large amount of labeled data for supervised learning in monocular depth estimation， a semi-supervised depth estimation framework AugDepth was proposed based on a teacher-student model. It operates by perturbing the data and training the model to learn depth consistency before and after the perturbation. Firstly， the smooth random intensity enhancement method was used to sample the intensity from the continuous domain. Multiple operations were randomly selected to increase the randomness of the data， and the output was enhanced by mixing the strength and weakness to prevent excessive disturbance. Then， considering the varying training difficulties of different unlabeled samples， while improving the model's inference of global information through Cutout， the Cutout strategy is adaptively adjusted based on the confidence level of unlabeled samples to enhance the model's generalization and learning abilities. The experimental results on the KITTI and NYU Deeph datasets show that AugDepth can significantly improve the accuracy of semi supervised depth estimation and exhibit good robustness in situations where labeled data is scarce.Key words：computer application； semi-supervised learning； data agumentation； monocular image； depth estimation

CLC Number:

TP391

Hong-wei ZHAO,Wei-min ZHOU. Semi⁃supervised monocular depth estimation framework based on data augmentation[J].Journal of Jilin University(Engineering and Technology Edition), 2025, 55(6): 2082-2088.

Figures/Tables 8

Fig.1

Table 1

Fig.2

Fig.3

Table 2

Quantitative results on the Eigen split of the KITTI dataset"

方法	监督方式	AbsRel	SqRel	RMSE	RMSElog	$δ 1$
DORN^［15］	有监督	0.072	0.307	2.727	0.120	0.932
LapDepth（Resnet50）	有监督	0.064	0.259	2.828	0.102	0.949
Monodepth2^［16］	自监督	0.080	0.466	3.681	0.127	0.926
FeatDepth^［17］	自监督	0.079	0.666	3.922	0.163	0.925
Cho^［5］	半监督	0.095	0.613	4.129	0.175	0.884
SemiDepth^［18］	半监督	0.078	0.417	3.464	0.126	0.923
Baek^［14］	半监督	0.071	0.316	3.049	0.111	0.941
本文	半监督	0.062	0.251	2.726	0.098	0.954

Table 2

Table 3

Quantitative results on the NYU-Depth"

方法	AbsRel	RMSE	$δ 1$
Eigen^［1］	0.158	0.641	0.769
DORN	0.115	0.509	0.828
BTS	0.112	0.352	0.882
LapDepth	0.110	0.393	0.885
DPT-Hybrid^［19］	0.110	0.357	0.904
Baek^［14］	0.109	0.392	0.894
Ours	0.105	0.395	0.889

Table 3

Table 4

Ablation studies on our AugDepth"

MT	$A s$	$A c$	AbsRel	$δ 1$
			0.066（supervised）	0.948（supervised）
√			0.066	0.949
√	√		0.065	0.950
√		√	0.064	0.952
√	√	√	0.062	0.954

Table 4

Table 5

Comparison of data augmentation effects"

方法	AbsRel	$δ 1$
RandAugment	0.066 0.065 0.064 0.065 0.064 0.062	0.951
Cutout		0.951
RandomAugment + Cutout		0.953
$A s$		0.950
$A c$		0.952
$A c + A s$		0.954

Table 5

References 19

[1]	Eigen D, Puhrsch C, Fergus R. Depth map predictionfrom a single image using a multi-scale deep network[C]∥Advances in Neural Information Processing Systems,Montreal, Canada, 2014: 2366-2374.
[2]	Song M, Lim S, Kim W. Monocular depth estimation using laplacian pyramid-based depth residuals[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2021, 31(11): 4381-4393.
[3]	Lee J H, Han M K, Ko D W, et al. From big to small: multi-scale local planar guidance for monocular depth estimation[J/OL].[2023-08-26].
[4]	Ji R, Li K, Wang Y, et al. Semi-supervised adversarial monocular depth estimation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020, 42(10): 2410-2422.
[5]	Cho J, Min D, Kim Y, et al. A large RGB-D dataset for semi-supervised monocular depth estimation[J/OL]. [2023-08-27].
[6]	Guo X, Li H, Yi S, et al. Learning monocular depth by distilling cross-domain stereo networks[C]∥Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany, 2018: 506-523.
[7]	Cubuk E D, Zoph B, Shlens J, et al. Randaugment: practical automated data augmentation with a reduced search space[C]∥Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops,Seattle, USA, 2020: 702-703.
[8]	Zhao Z, Yang L, Long S, et al. Augmentation matters: a simple-yet-effective approach to semi-supervisedsemantic segmentation[C]∥Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition,Vancouver, Canada,2023: 11350-11359.
[9]	Zhao Z, Long S, Pi J, et al. Instance-specific and model-adaptive supervision for semi-supervised semantic segmentation[C]∥Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Vancouver, Canada,2023: 23705-23714.
[10]	de Vries T, Taylor G W. Improved regularization of convolutional neural networks with cutout[J/OL].[2023-08-28].
[11]	Tarvainen A, Valpola H. Mean teachers are better rolemodels: weight-averaged consistency targets improve semi-supervised deep learning results[C]∥Advances in Neural Information Processing System,Vancouver, Canada, 2017: 1195-1204.
[12]	Yuan J, Liu Y, Shen C, et al. A simple baseline for semi-supervised semantic segmentation with strong data augmentation[C]∥IEEE/CVF International Conference on Computer Vision (ICCV), Montreal, Canada, 2021: 8209-8218.
[13]	Poggi M, Aleotti F, Tosi F, et al. On the uncertainty of self-supervised monocular depth estimation[C]∥Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition,Seattle, USA, 2020: 3227-3237.
[14]	Baek J, Kim G, Park S, et al. MaskingDepth: masked consistency regularization for semi-supervised monocular depth estimation[J/OL]. [2023-08-29].
[15]	Fu H, Gong M, Wang C, et al. Deep ordinal regression network for monocular depth estimation[C]∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Los Alamitos,USA, 2018: 2002-2011.
[16]	Godard C, Aodha O M, Firman M, et al. Digging into self-supervised monocular depth estimation[C]∥IEEE/CVF International Conference on Computer Vision (ICCV), Seoul, Korea, 2019: 3827-3837.
[17]	Shu C, Yu K, Duan Z, et al. Feature-metric loss for self-supervised learning of depth and egomotion[C]∥European Conference on Computer Vision,Glasgow, UK, 2020: 572-588.
[18]	Amiri A J, Loo S Y, Zhang H. Semi-supervised monocular depth estimation with left-right consistency using deep neural network[C]∥IEEE International Conference on Robotics and Biomimetics (ROBIO), Dali,China,2019: 602-607.
[19]	Ranftl R, Bochkovskiy A, Koltun V. Vision transformers for dense prediction[C]∥IEEE/CVF International Conference on Computer Vision (ICCV), Montreal, Canada, 2021: 12159-12168.

Related Articles 15

[1]	Xiang-jiu CHE,Yu-peng SUN. Graph node classification algorithm based on similarity random walk aggregation [J]. Journal of Jilin University(Engineering and Technology Edition), 2025, 55(6): 2069-2075.
[2]	Ping-ping LIU,Wen-li SHANG,Xiao-yu XIE,Xiao-kang YANG. Unbalanced image classification algorithm based on fine⁃grained analysis [J]. Journal of Jilin University(Engineering and Technology Edition), 2025, 55(6): 2122-2130.
[3]	Rui-shan DU,Zi-shan WANG. Multi perspective facial expression recognition algorithm based on spatiotemporal attention [J]. Journal of Jilin University(Engineering and Technology Edition), 2025, 55(6): 2097-2102.
[4]	Bin WEN,Shun PENG,Chao YANG,Yan-jun SHEN,Hui LI. Multi⁃depth adaptive fusion dehazing generation network [J]. Journal of Jilin University(Engineering and Technology Edition), 2025, 55(6): 2103-2113.
[5]	Hai-peng CHEN,Shi-bo ZHANG,Ying-da LYU. Multi⁃scale context⁃aware and boundary⁃guided image manipulation detection method [J]. Journal of Jilin University(Engineering and Technology Edition), 2025, 55(6): 2114-2121.
[6]	Qing-liang JIN,Xin-sen ZHOU,Yi CHEN,Cheng-wen WU. Predictive model for identifying innovative university talents based on the swarm intelligence evolution enhanced kernel extreme learning machine [J]. Journal of Jilin University(Engineering and Technology Edition), 2025, 55(5): 1763-1771.
[7]	Yan-fei LI,Jia-ning WU. Human pose local feature recognition algorithm based on improved RBF neural network [J]. Journal of Jilin University(Engineering and Technology Edition), 2025, 55(5): 1749-1755.
[8]	Yun-fei QIU,Hong-miao YU,Xiang WANG. 3D laser point cloud recognition based on point-to-point feature algorithm and SVD decomposition [J]. Journal of Jilin University(Engineering and Technology Edition), 2025, 55(5): 1735-1741.
[9]	Hong XIAO,Xian-de LIU. A facial subtle feature recognition algorithm considering the correlation between learning interests and micro expressions [J]. Journal of Jilin University(Engineering and Technology Edition), 2025, 55(5): 1728-1734.
[10]	Ya-li XUE,Tong-an YU,Shan CUI,Li-zun ZHOU. Infrared small target detection based on cascaded nested U-Net [J]. Journal of Jilin University(Engineering and Technology Edition), 2025, 55(5): 1714-1721.
[11]	Bin WEN,Yi-fu DING,Chao YANG,Yan-jun SHEN,Hui LI. Self-selected architecture network for traffic sign classification [J]. Journal of Jilin University(Engineering and Technology Edition), 2025, 55(5): 1705-1713.
[12]	Yue HOU,Jin-song GUO,Wei LIN,Di ZHANG,Yue WU,Xin ZHANG. Multi-view video speed extraction method that can be segmented across lane demarcation lines [J]. Journal of Jilin University(Engineering and Technology Edition), 2025, 55(5): 1692-1704.
[13]	De-qiang CHENG,Wei-chen WANG,Cheng-gong HAN,Chen LYU,Qi-qi KOU. Self-supervised monocular depth estimation based on improved densenet and wavelet decomposition [J]. Journal of Jilin University(Engineering and Technology Edition), 2025, 55(5): 1682-1691.
[14]	Hong-wei ZHAO,Ming-zhu ZHOU,Ping-ping LIU,Qiu-zhan ZHOU. Medical image segmentation based on confident learning and collaborative training [J]. Journal of Jilin University(Engineering and Technology Edition), 2025, 55(5): 1675-1681.
[15]	You-wei WANG,Ao LIU,Li-zhou FENG. New method for text sentiment classification based on knowledge distillation and comment time [J]. Journal of Jilin University(Engineering and Technology Edition), 2025, 55(5): 1664-1674.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

Comments

Recommended 10

[1]	Shi Guo-biao,Shen Rong-wei,Lin Yi . Modeling and simulation of electric power steering system[J]. 吉林大学学报(工学版), 2007, 37(01): 31 -36 .
[2]	CUI Yan, ZHANG Wan-xi, LIU Fu-chang, ZHANG Cheng-yi, LI Qin. Preparation of Waterborne Block Type Nanostructural[J]. 吉林大学学报(工学版), 2005, 35(05): 482 -0485 .
[3]	Pei Shi-hui，Zhao Hong-wei，Zhang Xiao-lin，Wang Peng . Distributed key distribution centre scheme based on Vandermonde matrix[J]. 吉林大学学报(工学版), 2007, 37(05): 1154 -1158 .
[4]	Yu Sheng-bao，Zhang Xian-tao，Chen Tian-qi，Wang Zhao-ming . Electrical detection with noncontact electrode[J]. 吉林大学学报(工学版), 2008, 38(02): 370 -0373 .
[5]	Zhang Han-zhuo, Jiang Zhong-hao, Lian Jian-she, Li Guang-yu . Influence of current density on synthesized technique and microstructure of nanocrystalline Cu deposition [J]. 吉林大学学报(工学版), 2007, 37(05): 1074 -1077 .
[6]	Yao Zhi-sheng, Shao Chun-fu, Xiong Zhi-hua, Yue Hao . Short-term traffic volumes forecasting of road network based on principal component analysis and support vector machine[J]. 吉林大学学报(工学版), 2008, 38(01): 48 -52 .
[7]	Yuan Rui, Ma Xu, Ma Cheng-lin, Wang Wei, Qiao Xin, Yang Dan. Virtual manufacturing and motion simulation of precision planter unit[J]. 吉林大学学报(工学版), 2006, 36(04): 523 -528 .
[8]	Xu An，Qiao Xiang-ming. Failure rate expression of complex equipment based on renewal theory[J]. 吉林大学学报(工学版), 2006, 36(03): 359 -0362 .
[9]	MIAO Ming， JIANG Bo， ZHANG Tao . Structure and functional properties of chickpea starches of Kabuli and Desi varieties[J]. 吉林大学学报(工学版), 2008, 38(06): 1495 -1500 .
[10]	SHI Wen-Xiao, LI Hai-Bei, GONG Jing. Technology of baton handover in TD SCDMA systems[J]. 吉林大学学报(工学版), 2009, 39(05): 1358 -1363 .

增强操作	增强策略细节
映射	返回原始图像
均衡化	均衡化图像的直方图
高斯模糊	用高斯核模糊图像
对比度	调整图像的对比度到［0.05，0.95］
锐度	调整图像的锐度到［0.05，0.95］
颜色	将图像的颜色平衡增强到［0.05，0.95］
亮度	调整图像的亮度到［0.05，0.95］
海报化	将每个像素减少到［4，8］位
太阳化	反转图像中高于［1，256］阈值的像素

Semi⁃supervised monocular depth estimation framework based on data augmentation

RICH HTML

PDF (PC)