Revisiting Single Image Depth Estimation: Toward Higher Resolution Maps with Accurate Object Boundaries

Abstract

This paper considers the problem of single image depth estimation. The employment of convolutional neural networks (CNNs) has recently brought about significant advancements in the research of this problem. However, most existing methods suffer from loss of spatial resolution in the estimated depth maps; a typical symptom is distorted and blurry reconstruction of object boundaries. In this paper, toward more accurate estimation with a focus on depth maps with higher spatial resolution, we propose two improvements to existing approaches. One is about the strategy of fusing features extracted at different scales, for which we propose an improved network architecture consisting of four modules: an encoder, decoder, multi-scale feature fusion module, and refinement module. The other is about loss functions for measuring inference errors used in training. We show that three loss terms, which measure errors in depth, gradients and surface normals, respectively, contribute to improvement of accuracy in an complementary fashion. Experimental results show that these two improvements enable to attain higher accuracy than the current state-of-the-arts, which is given by finer resolution reconstruction, for example, with small objects and object boundaries.

References in corpus (19)

• Rethinking Atrous Convolution for Semantic Image Segmentation
• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• Densely Connected Convolutional Networks
• Depth Map Prediction from a Single Image using a Multi-Scale Deep Network
• Image Restoration Using Very Deep Convolutional Encoder-Decoder Networks with Symmetric Skip Connections
• DeMoN: Depth and Motion Network for Learning Monocular Stereo
• Learning Deconvolution Network for Semantic Segmentation
• Holistically-Nested Edge Detection
• RedNet: Residual Encoder-Decoder Network for indoor RGB-D Semantic Segmentation
• Deep Ordinal Regression Network for Monocular Depth Estimation
• The Importance of Skip Connections in Biomedical Image Segmentation
• Sparse-to-Dense: Depth Prediction from Sparse Depth Samples and a Single Image
• Single-Image Depth Perception in the Wild
• Semi-Supervised Deep Learning for Monocular Depth Map Prediction
• Depth CNNs for RGB-D scene recognition: learning from scratch better than transferring from RGB-CNNs
• Depth from a Single Image by Harmonizing Overcomplete Local Network Predictions
• Discriminative Training of Deep Fully-connected Continuous CRF with Task-specific Loss
• Joint Prediction of Depths, Normals and Surface Curvature from RGB Images using CNNs
• Curve-Structure Segmentation from Depth Maps: A CNN-based Approach and Its Application to Exploring Cultural Heritage Objects

Cited by in corpus (1)

• Self-supervised Learning for Single View Depth and Surface Normal Estimation