Pyramid Feature Attention Network for Monocular Depth Prediction

arXiv:2403.01440v1 Announce Type: new
Abstract: Deep convolutional neural networks (DCNNs) have achieved great success in monocular depth estimation (MDE). However, few existing works take the contributions for MDE of different levels feature maps into account, leading to inaccurate spatial layout, ambiguous boundaries and discontinuous object surface in the prediction. To better tackle these problems, we propose a Pyramid Feature Attention Network (PFANet) to improve the high-level context features and low-level spatial features. In the proposed PFANet, we design a Dual-scale …

abstract arxiv attention convolutional neural networks cs.cv feature maps mde network networks neural networks prediction pyramid spatial success surface type