Deep Robust Single Image Depth Estimation Neural Network Using Scene Understanding

2019-06-07 · Haoyu Ren, Mostafa El-Khamy, Jungwon Lee

Single image depth estimation (SIDE) plays a crucial role in 3D computer vision. In this paper, we propose a two-stage robust SIDE framework that can perform blind SIDE for both indoor and outdoor scenes. At the first stage, the scene understanding module will categorize the RGB image into different depth-ranges. We introduce two different scene understanding modules based on scene classification and coarse depth estimation respectively. At the second stage, SIDE networks trained by the images of specific depth-range are applied to obtain an accurate depth map. In order to improve the accuracy, we further design a multi-task encoding-decoding SIDE network DS-SIDENet based on depthwise separable convolutions. DS-SIDENet is optimized to minimize both depth classification and depth regression losses. This improves the accuracy compared to a single-task SIDE network. Experimental results demonstrate that training DS-SIDENet on an individual dataset such as NYU achieves competitive performance to the state-of-art methods with much better efficiency. Ours proposed robust SIDE framework also shows good performance for the ScanNet indoor images and KITTI outdoor images simultaneously. It achieves the top performance compared to the Robust Vision Challenge (ROB) 2018 submissions.

📄 PDF Abstract BibTeX arXiv:1906.03279

Code (0)

등록된 구현이 없습니다.

Tasks

Depth Estimation General Classification Scene Classification Scene Understanding

To complete or to estimate, that is the question: A Multi-Task Approach to Depth Completion and Monocular Depth Estimation

2019-08-15 · Amir Atapour-Abarghouei, Toby P. Breckon

Robust three-dimensional scene understanding is now an ever-growing area of research highly relevant in many real-world applications such as autonomous driving and robotic navigation. In this paper, we propose a multi-ta…

Autonomous Driving Depth Completion Depth Estimation Monocular Depth Estimation+2

Single Image Depth Estimation: An Overview

2021-04-13 · Alican Mertan, Damien Jade Duff, Gozde Unal

We review solutions to the problem of depth estimation, arguably the most important subtask in scene understanding. We focus on the single image depth estimation problem. Due to its properties, the single image depth est…

Deep Learning Depth Estimation Scene Understanding Semantic Segmentation+1

MGNet: Monocular Geometric Scene Understanding for Autonomous Driving

2022-06-27 · ICCV 2021 10 · Markus Schön, Michael Buchholz, Klaus Dietmayer

We introduce MGNet, a multi-task framework for monocular geometric scene understanding. We define monocular geometric scene understanding as the combination of two known tasks: Panoptic segmentation and self-supervised m…

Autonomous Driving Depth Estimation GPU Monocular Depth Estimation+2

Multi-task Geometric Estimation of Depth and Surface Normal from Monocular 360° Images

2024-11-04 · Kun Huang, Fang-Lue Zhang, Fangfang Zhang, Yu-Kun Lai 외

Geometric estimation is required for scene understanding and analysis in panoramic 360{\deg} images. Current methods usually predict a single feature, such as depth or surface normal. These methods can lack robustness, e…

Multi-Task Learning Scene Understanding Surface Normal Estimation

Indoor Scene Structure Analysis for Single Image Depth Estimation

2015-06-01 · CVPR 2015 6 · Wei Zhuo, Mathieu Salzmann, Xuming He, Miaomiao Liu

We tackle the problem of single image depth estimation, which, without additional knowledge, suffers from many ambiguities. Unlike previous approaches that only reason locally, we propose to exploit the global structure …

Depth Estimation