THE Benchmark: Transferable Representation Learning for Monocular Height Estimation
Author:
Affiliation:
1. Chair of Data Science in Earth Observation, Technical University of Munich (TUM), Munich, Germany
2. School of Artificial Intelligence, Optics and Electronics (iOPEN), Northwestern Polytechnical University, Xi’an, China
Funder
German Federal Ministry of Education and Research
German Federal Ministry for Economic Affairs and Climate Action
H2020 European Research Council
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
Subject
General Earth and Planetary Sciences,Electrical and Electronic Engineering
Link
http://xplorestaging.ieee.org/ielx7/36/10006360/10251159.pdf?arnumber=10251159
Reference61 articles.
1. Boosting Monocular Depth Estimation Models to High-Resolution via Content-Adaptive Multi-Resolution Merging
2. Unified Perceptual Parsing for Scene Understanding
3. Look Deeper into Depth: Monocular Depth Estimation with Semantic Booster and Attention-Driven Loss
4. Adam: A method for stochastic optimization;kingma;arXiv 1412 6980,2014
5. Unsupervised Monocular Depth Estimation with Left-Right Consistency
Cited by 5 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
1. One for All: Toward Unified Foundation Models for Earth Vision;IGARSS 2024 - 2024 IEEE International Geoscience and Remote Sensing Symposium;2024-07-07
2. HeightFormer: A Multilevel Interaction and Image-Adaptive Classification–Regression Network for Monocular Height Estimation with Aerial Images;Remote Sensing;2024-01-11
3. Stereollax Net: Stereo Parallax-Based Deep Learning Network for Building Height Estimation;IEEE Transactions on Geoscience and Remote Sensing;2024
4. Weakly Supervised 3-D Building Reconstruction From Monocular Remote Sensing Images;IEEE Transactions on Geoscience and Remote Sensing;2024
5. Self-Supervised Pretraining With Monocular Height Estimation for Semantic Segmentation;IEEE Transactions on Geoscience and Remote Sensing;2024
1.学者识别学者识别
2.学术分析学术分析
3.人才评估人才评估
"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370
www.globalauthorid.com
TOP
Copyright © 2019-2024 北京同舟云网络信息技术有限公司 京公网安备11010802033243号 京ICP备18003416号-3