High Quality Monocular Depth Estimation via Transfer Learning

Ibraheem Alhashim, Peter Wonka
12/31/2018
cs.CV

Official code: ialhashim/DenseDepth (1,608 stars, GPL-3.0, PyTorch, last commit 2022-12-07).

Abstract

Accurate depth estimation from images is a fundamental task in many applications including scene understanding and reconstruction. Existing solutions for depth estimation often produce blurry approximations of low resolution. This paper presents a convolutional neural network for computing a high-resolution depth map given a single RGB image with the help of transfer learning. Following a standard encoder-decoder architecture, we leverage features extracted using high performing pre-trained networks when initializing our encoder along with augmentation and training strategies that lead to more accurate results. We show how, even for a very simple decoder, our method is able to achieve detailed high-resolution depth maps. Our network, with fewer parameters and training iterations, outperforms state-of-the-art on two datasets and also produces qualitatively better results that capture object boundaries more faithfully. Code and corresponding pre-trained weights are made publicly available.

View on arXivView PDF

Code Implementations(1)

ialhashim/DenseDepthOfficial100%
PyTorchGPL-3.0

High Quality Monocular Depth Estimation via Transfer Learning

1,608346Python, Jupyter NotebookDec 28, 20183 years agoGPL-3.0
deep-learningdeep-neural-networksdepth-estimationencoder-decoder-modelkeras-tensorflow+3 more

Similar Papers

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

91% match1 repo6742019

AdaBins: Depth Estimation using Adaptive Bins

90% match1 repo7842020

Deeper Depth Prediction with Fully Convolutional Residual Networks

90% match1 repo1.1k2016

Global-Local Path Networks for Monocular Depth Estimation with Vertical CutDepth

90% match1 repo2002022

URCDC-Depth: Uncertainty Rectified Cross-Distillation with CutFlip for Monocular Depth Estimation

89% match1 repo442023

Deep Ordinal Regression Network for Monocular Depth Estimation

88% match1 repo4712018

Cite this paper

@article{alhashim2018high,
  title  = {High Quality Monocular Depth Estimation via Transfer Learning},
  author = {Ibraheem Alhashim and Peter Wonka},
  year   = {2018},
  eprint = {1812.11941},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1812.11941}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/1812.11941.svg)](https://codeofpaper.com/paper/1812.11941)

Discussion