Monocular depth estimation based on dense connections

To solve the problems of blurred edges of depth map objects and poor image quality caused by the repetition of simple up-sampling operations in the current monocular depth estimation methods, a densely connected monocular depth estimation method was proposed.The method used an end-to-end encoder and decoder architecture for depth estimation from a single RGB image. The encoder introduced the high-performance convolutional neural network EfficientNet-B5, which could efficiently extract the global context features of images. The decoder was designed as a densely connected up-sampled feature pyramid structure to transfer global contextual features from low resolution to high resolution for higher quality depth maps. In addition, the depth estimation accuracy of object edges was further improved by designing a full-resolution multi-scale loss function.The training and testing results on the NYU Depth V2 indoor scene depth dataset and the KITTI outdoor scene depth dataset show that the proposed method can produce high-precision depth estimation results, and the predicted depth maps have clear edges and well-defined outlines.The designed ablation experiments could fully validate the reasonableness of the proposed method modules. © 2023 Huazhong University of Science and Technology. All rights reserved.