Detail Preserving Depth Estimation from a Single Image Using Attention Guided Networks

Abstract

Convolutional Neural Networks have demonstrated superior performance on single image depth estimation in recent years. These works usually use stacked spatial pooling or strided convolution to get high-level information which are common practices in classification task. However, depth estimation is a dense prediction problem and low-resolution feature maps usually generate blurred depth map which is undesirable in application. In order to produce high quality depth map, say clean and accurate, we propose a network consists of a Dense Feature Extractor (DFE) and a Depth Map Generator (DMG). The DFE combines ResNet and dilated convolutions. It extracts multi-scale information from input image while keeping the feature maps dense. As for DMG, we use attention mechanism to fuse multi-scale features produced in DFE. Our Network is trained end-to-end and does not need any post-processing. Hence, it runs fast and can predict depth map in about 15 fps. Experiment results show that our method is competitive with the state-of-the-art in quantitative evaluation, but can preserve better structural details of the scene depth.

arXiv commentPublished at IEEE International Conference on 3D Vision (3DV) 2018

References in corpus (7)

• Adam: A Method for Stochastic Optimization
• Very Deep Convolutional Networks for Large-Scale Image Recognition
• TensorFlow: A system for large-scale machine learning
• Depth Map Prediction from a Single Image using a Multi-Scale Deep Network
• Learning Depth from Single Monocular Images Using Deep Convolutional Neural Fields
• Recurrent Models of Visual Attention
• Depth Extraction from Video Using Non-parametric Sampling

Cited by in corpus (8)

• AdaBins: Depth Estimation using Adaptive Bins
• High Quality Monocular Depth Estimation via Transfer Learning
• NVS-MonoDepth: Improving Monocular Depth Prediction with Novel View Synthesis
• Conf-Net: Toward High-Confidence Dense 3D Point-Cloud with Error-Map Prediction
• Improving Monocular Depth Estimation by Leveraging Structural Awareness and Complementary Datasets
• Depth Estimation using Weighted-loss and Transfer Learning
• Weakly-Supervised Monocular Depth Estimationwith Resolution-Mismatched Data
• Boundary-induced and scene-aggregated network for monocular depth prediction