URCDC-Depth: Uncertainty Rectified Cross-Distillation With CutFlip for Monocular Depth Estimation
- 30 August 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 26 (15209210) , 3341-3353
Abstract
This work aims to estimate a high-quality depth map from a single RGB image. Due to the lack of depth clues, making full use of the long-range correlation and local information is critical for accurate depth estimation. To this end, we introduce an uncertainty rectified cross-distillation between the Transformer and convolutional neural network (CNN) to achieve a comprehensive depth estimator. Specifically, we utilize the depth estimates from the Transformer branch and CNN branch as pseudo labels to teach each other. At the same time, the pixel-wise depth uncertainty is modeled to mitigate the negative impact of noisy pseudo labels. To avoid the large capacity gap induced by the strong Transformer branch deteriorating the cross-distillation, we transfer the feature maps from the Transformer to the CNN and develop coupling units to assist the weak CNN branch in leveraging the transferred features. Furthermore, we introduce CutFlip, a surprisingly simple yet highly effective data augmentation technique, which forces the model to focus on more valuable depth reasoning clues apart from the vertical image position. Extensive experiments demonstrate that our model, termed URCDC-Depth , exceeds in performance previous state-of-the-art approaches on the KITTI, NYU-Depth-v2 and SUN RGB-D datasets, with no additional computational burden in the evaluation phase. The source code will be publicly available upon acceptance.Keywords
All Related Versions
Funding Information
- National Natural Science Foundation of China (62333023, U1909215)
- A*STAR Singapore
- MTC Programmatic Funds (M23L7b0021)
- Key Research and Development Program of Zhejiang Province (2021C03050)
- Scientific Research Project of Agriculture and Social Development of Hangzhou (20212013B11)
- National Natural Science Foundation of China (61620106012, 61573048)
This publication has 60 references indexed in Scilit:
- DepthFormer: Exploiting Long-range Correlation and Local Information for Accurate Monocular Depth EstimationMachine Intelligence Research, 2023
- Boosting LightWeight Depth Estimation via Knowledge Distillation2023
- Uncertainty Quantification in Depth Estimation via Constrained Ordinal Regression2022
- Gradient-Based Uncertainty for Monocular Depth Estimation2022
- Self-Supervised monocular depth and ego-Motion estimation in endoscopy: Appearance flow to the rescueMedical Image Analysis, 2022
- Cross-modal distillation for RGB-depth person re-identificationComputer Vision and Image Understanding, 2022
- Guiding Monocular Depth Estimation Using Depth-Attention Volume2020
- Modality Distillation with Multiple Stream Networks for Action Recognition2018
- Supervising the New with the Old: Learning SFM from SFM2018
- Indoor Segmentation and Support Inference from RGBD Images2012