A Compromise Principle in Deep Monocular Depth Estimation

08/28/2017
by   Huan Fu, et al.
0

Monocular depth estimation, which plays a key role in understanding 3D scene geometry, is fundamentally an ill-posed problem. Existing methods based on deep convolutional neural networks (DCNNs) have examined this problem by learning convolutional networks to estimate continuous depth maps from monocular images. However, we find that training a network to predict a high spatial resolution continuous depth map often suffers from poor local solutions. In this paper, we hypothesize that achieving a compromise between spatial and depth resolutions can improve network training. Based on this "compromise principle", we propose a regression-classification cascaded network (RCCN), which consists of a regression branch predicting a low spatial resolution continuous depth map and a classification branch predicting a high spatial resolution discrete depth map. The two branches form a cascaded structure allowing the classification and regression branches to benefit from each other. By leveraging large-scale raw training datasets and some data augmentation strategies, our network achieves top or state-of-the-art results on the NYU Depth V2, KITTI, and Make3D benchmarks.

READ FULL TEXT

page 6

page 7

page 9

research
06/06/2018

Deep Ordinal Regression Network for Monocular Depth Estimation

Monocular depth estimation, which plays a crucial role in understanding ...
research
09/06/2022

Crowdsourced-based Deep Convolutional Networks for Urban Flood Depth Mapping

Successful flood recovery and evacuation require access to reliable floo...
research
02/21/2023

Depth Estimation and Image Restoration by Deep Learning from Defocused Images

Monocular depth estimation and image deblurring are two fundamental task...
research
01/29/2019

Attention-based Context Aggregation Network for Monocular Depth Estimation

Depth estimation is a traditional computer vision task, which plays a cr...
research
07/24/2019

From Big to Small: Multi-Scale Local Planar Guidance for Monocular Depth Estimation

Estimating accurate depth from a single image is challenging, because it...
research
04/17/2020

DepthNet Nano: A Highly Compact Self-Normalizing Neural Network for Monocular Depth Estimation

Depth estimation is an active area of research in the field of computer ...
research
09/24/2018

Sparse-to-Continuous: Enhancing Monocular Depth Estimation using Occupancy Maps

This paper addresses the problem of single image depth estimation (SIDE)...

Please sign up or login with your details

Forgot password? Click here to reset