Monocular Depth Estimation with Directional Consistency by Deep Networks

Abstract

As processing power has become more available, more human-like artificial intelligences are created to solve image processing tasks that we are inherently good at. As such we propose a model that estimates depth from a monocular image. Our approach utilizes a combination of structure from motion and stereo disparity. We estimate a pose between the source image and a different viewpoint and a dense depth map and use a simple transformation to reconstruct the image seen from said viewpoint. We can then use the real image at that viewpoint to act as supervision to train out model. The metric chosen for image comparison employs standard L1 and structural similarity and a consistency constraint between depth maps as well as smoothness constraint. We show that similar to human perception utilizing the correlation within the provided data by two different approaches increases the accuracy and outperforms the individual components.

References in corpus (13)

• Adam: A Method for Stochastic Optimization
• TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
• Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)
• Stereo Matching by Training a Convolutional Neural Network to Compare Image Patches
• Unsupervised CNN for Single View Depth Estimation: Geometry to the Rescue
• Loss Functions for Neural Networks for Image Processing
• Unsupervised Learning of Depth and Ego-Motion from Video
• Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-Scale Convolutional Architecture
• Spatial Transformer Networks
• Unsupervised Monocular Depth Estimation with Left-Right Consistency
• Crafting GBD-Net for Object Detection
• Left-Right Comparative Recurrent Model for Stereo Matching
• Deep3D: Fully Automatic 2D-to-3D Video Conversion with Deep Convolutional Neural Networks