IEEE Transactions on Multimedia · 2023 · 49 citations · 46 references
ComputingComputer ScienceComputer VisionDigital ImagingMachine Vision3D Imaging3D ReconstructionDeep LearningDepth EstimationImage Feature EngineeringScene UnderstandingConvolutional Neural NetworksData AugmentationDeep Image FeaturesDepth Map EstimationDisparity EstimationMonocular Depth EstimationSingle-image Depth EstimationTransformer Models
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 <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">URCDC-Depth</b> , 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. The source code is available at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/ShuweiShao/URCDC-Depth</uri> .
46
Deep Residual Learning for Image Recognition
Kaiming He, Xiangyu Zhang, Shaoqing Ren et al. · 2016 · 222.1K citations · Full text
DROPS (Schloss Dagstuhl – Leibniz Center for Informatics) · 2023 · 76.3K citations · Full text
Densely Connected Convolutional Networks
Gao Huang, Zhuang Liu, Laurens van der Maaten et al. · 2017 · 44.7K citations
Feature Pyramid Networks for Object Detection
Tsung-Yi Lin, Piotr Dollár, Ross Girshick et al. · 2017 · 28.7K citations