The Constraints between Edge Depth and Uncertainty for Monocular Depth Estimation

The self-supervised monocular depth estimation paradigm has become an important branch of computer vision depth-estimation tasks. However, the depth estimation problem arising from object edge depth pulling or occlusion is still unsolved. The grayscale discontinuity of object edges leads to a relatively high depth uncertainty of pixels in these regions. We improve the geometric edge prediction results by taking uncertainty into account in the depth-estimation task. To this end, we explore how uncertainty affects this task and propose a new self-supervised monocular depth estimation technique based on multi-scale uncertainty. In addition, we introduce a teacher–student architecture in models and investigate the impact of different teacher networks on the depth and uncertainty results. We evaluate the performance of our paradigm in detail on the standard KITTI dataset. The experimental results show that the accuracy of our method increased from 87.7% to 88.2%, the AbsRel error rate decreased from 0.115 to 0.11, the SqRel error rate decreased from 0.903 to 0.822, and the RMSE error rate decreased from 4.863 to 4.686 compared with the benchmark Monodepth2. Our approach has a positive impact on the problem of texture replication or inaccurate object boundaries, producing sharper and smoother depth images.

Download Full-text

Monocular Depth Estimation Based on Multi-Scale Depth Map Fusion

IEEE Access ◽

10.1109/access.2021.3076346 ◽

2021 ◽

pp. 1-1

Author(s):

Xin Yang ◽

Qingling Chang ◽

Xinglin Liu ◽

Siyuan He ◽

Yan Cui

Keyword(s):

Depth Map ◽

Depth Estimation ◽

Multi Scale ◽

Monocular Depth

Download Full-text

DCPNet: A Densely Connected Pyramid Network for Monocular Depth Estimation

Sensors ◽

10.3390/s21206780 ◽

2021 ◽

Vol 21 (20) ◽

pp. 6780

Author(s):

Zhitong Lai ◽

Rui Tian ◽

Zhiguo Wu ◽

Nannan Ding ◽

Linjian Sun ◽

...

Keyword(s):

Multiple Scales ◽

Feature Fusion ◽

State Of The Art ◽

Depth Estimation ◽

Multi Scale ◽

Pyramid Structure ◽

Benchmark Datasets ◽

The Common ◽

Monocular Depth ◽

Multiple Stages

Pyramid architecture is a useful strategy to fuse multi-scale features in deep monocular depth estimation approaches. However, most pyramid networks fuse features only within the adjacent stages in a pyramid structure. To take full advantage of the pyramid structure, inspired by the success of DenseNet, this paper presents DCPNet, a densely connected pyramid network that fuses multi-scale features from multiple stages of the pyramid structure. DCPNet not only performs feature fusion between the adjacent stages, but also non-adjacent stages. To fuse these features, we design a simple and effective dense connection module (DCM). In addition, we offer a new consideration of the common upscale operation in our approach. We believe DCPNet offers a more efficient way to fuse features from multiple scales in a pyramid-like network. We perform extensive experiments using both outdoor and indoor benchmark datasets (i.e., the KITTI and the NYU Depth V2 datasets) and DCPNet achieves the state-of-the-art results.

Download Full-text

Monocular Depth Estimation Based on Multi-Scale Graph Convolution Networks

IEEE Access ◽

10.1109/access.2019.2961606 ◽

2020 ◽

Vol 8 ◽

pp. 997-1009

Author(s):

Junwei Fu ◽

Jun Liang ◽

Ziyang Wang

Keyword(s):

Depth Estimation ◽

Multi Scale ◽

Monocular Depth

Download Full-text

Exploring the Influence of Teacher-Student Interaction on University Students’ Self-Efficacy in the Flipped Classroom

Journal of Education and Learning ◽

10.5539/jel.v10n2p84 ◽

2021 ◽

Vol 10 (2) ◽

pp. 84

Author(s):

Lin Li ◽

Shanshan Yang

Keyword(s):

Undergraduate Students ◽

Self Efficacy ◽

Flipped Classroom ◽

Positive Impact ◽

Teaching Quality ◽

Student Interaction ◽

Student Centered Learning ◽

Teacher Student ◽

Teacher Student Interaction ◽

The Impact

The purpose of this study is to explore the impact of teacher-student interaction on undergraduate students’ self-efficacy in a Chinese university setting. Students came from natural science, management, economics, medicine, engineering and humanities. The empirical results demonstrate that teacher-student interaction has positive impact on students’ self-efficacy and their preference of the flipped classroom. Furthermore, the positive relationship between teacher-student interaction and students’ self-efficacy is partially mediated by students’ preference of the flipped classroom. Educators should focus on student-centered learning and motivate students’ preference of the flipped classroom. Students should be encouraged to actively participate in the flipped learning as well. It contributes to the reform of the flipped classroom and improvement of teaching quality in the universities.

Download Full-text

Structure-Aware Residual Pyramid Network for Monocular Depth Estimation

Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence ◽

10.24963/ijcai.2019/98 ◽

2019 ◽

Cited By ~ 4

Author(s):

Xiaotian Chen ◽

Xuejin Chen ◽

Zheng-Jun Zha

Keyword(s):

Local Structure ◽

Feature Fusion ◽

Depth Estimation ◽

Image Features ◽

Underlying Structure ◽

Complex Scene ◽

Multi Scale ◽

Depth Prediction ◽

Scale Structures ◽

Monocular Depth

Monocular depth estimation is an essential task for scene understanding. The underlying structure of objects and stuff in a complex scene is critical to recovering accurate and visually-pleasing depth maps. Global structure conveys scene layouts, while local structure reflects shape details. Recently developed approaches based on convolutional neural networks (CNNs) significantly improve the performance of depth estimation. However, few of them take into account multi-scale structures in complex scenes. In this paper, we propose a Structure-Aware Residual Pyramid Network (SARPN) to exploit multi-scale structures for accurate depth prediction. We propose a Residual Pyramid Decoder (RPD) which expresses global scene structure in upper levels to represent layouts, and local structure in lower levels to present shape details. At each level, we propose Residual Refinement Modules (RRM) that predict residual maps to progressively add finer structures on the coarser structure predicted at the upper level. In order to fully exploit multi-scale image features, an Adaptive Dense Feature Fusion (ADFF) module, which adaptively fuses effective features from all scales for inferring structures of each scale, is introduced. Experiment results on the challenging NYU-Depth v2 dataset demonstrate that our proposed approach achieves state-of-the-art performance in both qualitative and quantitative evaluation. The code is available at https://github.com/Xt-Chen/SARPN.

Download Full-text