Image-based 3D reconstruction for Multi-Scale civil and infrastructure Projects: A review from 2012 to 2022 with new perspective from deep learning methods

Review Construction & Building Technology

Deep learning-based 3D reconstruction of scaffolds using a robot dog

Juhyeon Kim et al.

Summary: The study proposes an automatic scaffold 3D reconstruction method using 3D point cloud data obtained by a robot dog, achieving a high accuracy of 90.84% through 3D semantic segmentation and automatic CAD model formation.

AUTOMATION IN CONSTRUCTION (2022)

添加到收藏夹

Article Computer Science, Interdisciplinary Applications

Automated inspection and monitoring of member deformation in grid structures

Xiao-Chen Wei et al.

Summary: This paper proposes a deformation inspection and monitoring method for grid structures using image-based 3D reconstruction, which accurately recognizes and extracts the deformed shapes of crooked members through a new automated recognition and extraction algorithm. In experiments, the average error of deformation measurements using image-based 3D reconstruction is within 1 mm compared to laser scanning, validating the effectiveness of the proposed method in on-site inspection and monitoring.

COMPUTER-AIDED CIVIL AND INFRASTRUCTURE ENGINEERING (2022)

添加到收藏夹

Article Computer Science, Software Engineering

Instant Neural Graphics Primitives with a Multiresolution Hash Encoding

Thomas Mueller et al.

Summary: The research introduces a versatile new input encoding that allows for a reduction in the cost of training and evaluation by using a multiresolution hash table in neural networks.

ACM TRANSACTIONS ON GRAPHICS (2022)

添加到收藏夹

Article Construction & Building Technology

A city-scale inverse modelling method for air pollutant source determination

Yi Wang et al.

Summary: Accurate and rapid identification of pollutant sources is crucial for protecting public health. The adjoint probability method used in this research shows high accuracy and applicability in determining air pollutant sources in urban areas. This method can provide guidance for sensor distribution and selection.

SUSTAINABLE CITIES AND SOCIETY (2022)

添加到收藏夹

Article Construction & Building Technology

Sewer defect instance segmentation, localization, and 3D reconstruction for sewer floating capsule robots

Xu Fang et al.

Summary: This study proposes a sewer detection framework based on computer vision technology for the sewer floating capsule robot, which can detect sewer defects in real-time and achieve three-dimensional reconstruction. The proposed method, using the improved mask regional convolutional neural network and data augmentation, demonstrates good performance and robustness.

AUTOMATION IN CONSTRUCTION (2022)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

RC-MVSNet: Unsupervised Multi-View Stereo with Neural Rendering

Di Chang et al.

Summary: In this paper, we propose a novel approach called RC-MVSNet that uses neural rendering to solve the ambiguity issues in correspondences among different views in unsupervised Multi-View Stereo. By introducing a depth rendering consistency loss and a reference view synthesis loss, we achieve accurate correspondences even in scenarios with non-Lambertian surfaces and occlusions.

COMPUTER VISION, ECCV 2022, PT XXXI (2022)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

BungeeNeRF: Progressive Neural Radiance Field for Extreme Multi-scale Scene Rendering

Yuanbo Xiangli et al.

Summary: This work introduces BungeeNeRF, a progressive neural radiance field that achieves level-of-detail rendering across drastically varied scales. By progressively activating high-frequency channels and unfolding more complex details, BungeeNeRF demonstrates superiority in modeling diverse multi-scale scenes.

COMPUTER VISION - ECCV 2022, PT XXXII (2022)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

Block-NeRF: Scalable Large Scene Neural View Synthesis

Matthew Tancik et al.

Summary: We propose a variant called Block-NeRF to represent large-scale environments. By decomposing the scene into individually trained NeRFs, rendering time can be decoupled from scene size, enabling rendering in arbitrarily large environments. We also introduce several architectural changes to make NeRF robust to different environmental conditions, and a procedure for aligning appearance between adjacent NeRFs for seamless combination.

2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR) (2022)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

Ref-NeRF: Structured View-Dependent Appearance for Neural Radiance Fields

Dor Verbin et al.

Summary: NeRF excels at representing fine geometric structures with smoothly varying view-dependent appearance, but often fails to accurately capture and reproduce the appearance of glossy surfaces. Ref-NeRF addresses this limitation by introducing a representation of reflected radiance and structuring this function using a collection of spatially-varying scene properties, significantly improving the realism and accuracy of specular reflections when combined with a regularizer on normal vectors.

2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022) (2022)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

EfficientNeRF - Efficient Neural Radiance Fields

Tao Hu et al.

Summary: This paper introduces an efficient NeRF-based method called EfficientNeRF for representing 3D scenes and synthesizing novel-view images. By proposing effective and crucial sampling methods as well as a novel data structure, it significantly improves the sampling efficiency and rendering speed while maintaining competitive accuracy.

2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR) (2022)

添加到收藏夹

Article Engineering, Civil

3D reconstruction and automatic leakage defect quantification of metro tunnel based on SfM-Deep learning method

Yadong Xue et al.

Summary: This paper proposes a novel SfM-Deep learning method for tunnel inspection, which combines the deep learning model and the 3D reconstruction method based on structure from motion (SfM). The method can help engineers efficiently carry out intelligent tunnel detection by constructing high-quality 3D tunnel models and realizing the visualization of leakage defects.

UNDERGROUND SPACE (2022)

添加到收藏夹

Review Computer Science, Information Systems

Single image 3D object reconstruction based on deep learning: A review

Kui Fu et al.

Summary: This paper discusses the challenges of reconstructing 3D objects from a single image using deep learning technology, reviews encoders, decoders, and training details, introduces datasets and evaluation metrics, conducts experiments to compare the advantages and disadvantages of different reconstruction methods, and provides some related application examples involving single image 3D reconstruction.

MULTIMEDIA TOOLS AND APPLICATIONS (2021)

添加到收藏夹

Article Computer Science, Artificial Intelligence

A 3D template-based point generation network for 3D reconstruction from single images

Anny Yuniarti et al.

Summary: Learning-based methods for 3D reconstruction have gained attention due to their performance in image segmentation and classification. This paper introduces a new framework for 3D reconstruction of 2D images using a 3D template-based point generation network, which shows better performance than existing methods in terms of Chamfer distance on the ShapeNet dataset.

APPLIED SOFT COMPUTING (2021)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Deep Learning for 3D Point Clouds: A Survey

Yulan Guo et al.

Summary: Recently, deep learning on point clouds has been gaining more attention, but it is still in its early stages due to the unique challenges faced in processing point clouds with deep neural networks.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2021)

添加到收藏夹

Article Geography, Physical

IMGTR: Image-triangle based multi-view 3D reconstruction for urban scenes

Zhihua Hu et al.

Summary: The paper introduces an image-triangle based multi-view 3D reconstruction method, which can reconstruct complex urban structures more accurately and achieve higher fidelity in planar urban structures. Qualitative and quantitative experiments show that the proposed method outperforms some recently released multi-view stereo algorithms in terms of position accuracy.

ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING (2021)

添加到收藏夹

Review Computer Science, Information Systems

A review of three dimensional reconstruction techniques

Jonathan Then Sien Phang et al.

Summary: Three dimensional (3D) modeling is crucial for aggregating multiple viewpoints and extracting geometrical information. The core computational process in 3D modeling is 3D reconstruction, which can be categorized into statistical models, discriminative learning models, and generative learning models. These models learn spatial and geometric features through data-driven training or direct inference.

MULTIMEDIA TOOLS AND APPLICATIONS (2021)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Image-Based 3D Object Reconstruction: State-of-the-Art and Trends in the Deep Learning Era

Xian-Feng Han et al.

Summary: This article provides a comprehensive survey of recent developments in image-based 3D reconstruction using convolutional neural networks, focusing on estimating the 3D shape of generic objects from single or multiple RGB images. The survey analyzes and compares the performance of key papers, summarizes open problems in the field, and discusses promising directions for future research.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2021)

添加到收藏夹

Article Computer Science, Interdisciplinary Applications

The journal coverage of Web of Science, Scopus and Dimensions: A comparative analysis

Vivek Kumar Singh et al.

Summary: This article compares the journal coverage of Web of Science, Scopus, and Dimensions databases, revealing significant differences among them, with Web of Science being the most selective and Dimensions being the most exhaustive.

SCIENTOMETRICS (2021)

添加到收藏夹

Article Environmental Sciences

3D Reconstruction of Coastal Cliffs from Fixed-Wing and Multi-Rotor UAS: Impact of SfM-MVS Processing Parameters, Image Redundancy and Acquisition Geometry

Gil Goncalves et al.

Summary: This study analyzed the key parameters and image acquisition strategies for generating cliff point clouds using Structure-from-Motion and Multi View Stereo technology on drones. The results showed that optimizing parameters and reducing image overlap can improve the accuracy and density of the point cloud.

REMOTE SENSING (2021)

添加到收藏夹

Article Environmental Sciences

BIM Supported Surveying and Imaging Combination for Heritage Conservation

Pedro Martin-Lerones et al.

Summary: This paper discusses the process of processing 3D point cloud data for use in BIM software to improve efficiency and accuracy in heritage asset management. Specific H-BIM specifications have been developed for heritage projects, and non-proprietary formats like IFC are used for information exchange.

REMOTE SENSING (2021)

添加到收藏夹

Article Construction & Building Technology

Semi-automated luminance map re-projection via high dynamic range imaging and indoor space 3-D reconstruction

Michael Kim et al.

Summary: This paper presents a semi-automated robust framework for monitoring luminance within the field of view of occupants using a HDRI camera, with a new HDRI pipeline and photogrammetry framework employed. The framework showed reasonable performance in a real daylit office environment.

AUTOMATION IN CONSTRUCTION (2021)

添加到收藏夹

Article Construction & Building Technology

Three-Dimensional Object Detection with Deep Neural Networks for Automatic As-Built Reconstruction

Yongzhi Xu et al.

Summary: This study aims to develop an end-to-end, fully automatic, and object-level reconstruction approach to converting point clouds of non-Manhattan and multiroom buildings into 3D models. By using a two-stage 3D object-detection method with region-based convolutional neural networks (R-CNN) and feature fusion between sparse 3D and two-dimensional bird's eye view (BEV) feature maps, the generality and efficiency of modeling building primitives have been improved.

JOURNAL OF CONSTRUCTION ENGINEERING AND MANAGEMENT (2021)

添加到收藏夹

Review Chemistry, Multidisciplinary

Review of Image-Based 3D Reconstruction of Building for Automated Construction Progress Monitoring

Jingguo Xue et al.

Summary: This paper investigates how the actual status of construction sites is recorded and analyzed through digital images, and emphasizes the key role of 3D reconstruction in project schedule monitoring. It also points out the challenges researchers face in choosing research methods and paths, as well as future research directions and knowledge gaps.

APPLIED SCIENCES-BASEL (2021)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

M3VSNET: UNSUPERVISED MULTI-METRIC MULTI-VIEW STEREO NETWORK

Baichuan Huang et al.

Summary: This paper introduces a novel unsupervised multi-metric MVS network (M(3)VSNet) for dense point cloud reconstruction, achieving better performance without supervision, improving reconstruction accuracy and continuity through a multi-metric loss function and normal-depth consistency.

2021 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP) (2021)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

Multi-Category Mesh Reconstruction From Image Collections

Alessandro Simoni et al.

Summary: The paper introduces an alternative approach to inferring the textured mesh of objects by training on multiple object categories without specific 3D templates. Experimental results show that the framework can distinguish between different object categories in an unsupervised manner and achieve comparable or state-of-the-art results.

2021 INTERNATIONAL CONFERENCE ON 3D VISION (3DV 2021) (2021)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fields

Jonathan T. Barron et al.

Summary: Mip-NeRF is an extension of NeRF that reduces aliasing artifacts, improves fine detail representation, and is more efficient in speed and size compared to NeRF.

2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021) (2021)

添加到收藏夹

Article Computer Science, Software Engineering

POINTCLEANNET: Learning to Denoise and Remove Outliers from Dense Point Clouds

Marie-Julie Rakotosaona et al.

COMPUTER GRAPHICS FORUM (2020)

添加到收藏夹

Review Computer Science, Information Systems

A Review of Techniques for 3D Reconstruction of Indoor Environments

Zhizhong Kang et al.

ISPRS INTERNATIONAL JOURNAL OF GEO-INFORMATION (2020)

添加到收藏夹

Article Environmental Sciences

Low-Cost and Efficient Indoor 3D Reconstruction through Annotated Hierarchical Structure-from-Motion

Youli Ding et al.

REMOTE SENSING (2019)

添加到收藏夹

Review Computer Science, Artificial Intelligence

Applications of 3D point cloud data in the construction industry: A fifteen-year review from 2004 to 2018

Qian Wang et al.

ADVANCED ENGINEERING INFORMATICS (2019)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

Total Denoising: Unsupervised Learning of 3D Point Cloud Cleaning

Pedro Hermosilla et al.

2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019) (2019)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

Efficient 3D Reconstruction and Streaming for Group-Scale Multi-Client Live Telepresence

Patrick Stotko et al.

2019 IEEE INTERNATIONAL SYMPOSIUM ON MIXED AND AUGMENTED REALITY (ISMAR) (2019)

添加到收藏夹

Article Computer Science, Artificial Intelligence

A review of 3D reconstruction techniques in civil engineering and their applications

Zhiliang Ma et al.

ADVANCED ENGINEERING INFORMATICS (2018)

添加到收藏夹

Article Construction & Building Technology

Automatic building building information model reconstruction in high-density urban areas: Augmenting multi-source data with architectural knowledge

Ke Chen et al.

AUTOMATION IN CONSTRUCTION (2018)

添加到收藏夹

Article Computer Science, Software Engineering

PCPNET Learning Local Shape Properties from Raw Point Clouds

Paul Guerrero et al.

COMPUTER GRAPHICS FORUM (2018)

添加到收藏夹

Article Construction & Building Technology

Image-based 3D reconstruction using traditional and UAV datasets for analysis of road pavement distress

Laura Inzerillo et al.

AUTOMATION IN CONSTRUCTION (2018)

添加到收藏夹

Review Computer Science, Information Systems

Deep Learning in Data-Driven Pavement Image Analysis and Automated Distress Detection: A Review

Kasthurirangan Gopalakrishnan

DATA (2018)

添加到收藏夹

Article Engineering, Civil

Bridge inspection: human performance, unmanned aerial systems and automation

Sattar Dorafshan et al.

JOURNAL OF CIVIL STRUCTURAL HEALTH MONITORING (2018)

添加到收藏夹

Article Geography, Physical

Detecting repetitive structures on building footprints for the purposes of 3D modeling and reconstruction

Hongchao Fan et al.

INTERNATIONAL JOURNAL OF DIGITAL EARTH (2017)

添加到收藏夹

Article Computer Science, Interdisciplinary Applications

Hierarchical Dense Structure-from-Motion Reconstructions for Infrastructure Condition Assessment

Ali Khaloo et al.

JOURNAL OF COMPUTING IN CIVIL ENGINEERING (2017)

添加到收藏夹

Review Computer Science, Interdisciplinary Applications

Image-Based Technologies for Constructing As-Is Building Information Models for Existing Buildings

Qiuchen Lu et al.

JOURNAL OF COMPUTING IN CIVIL ENGINEERING (2017)

添加到收藏夹

Article Computer Science, Information Systems

Comparing keywords plus of WOS and author keywords: A case study of patient adherence research

Juan Zhang et al.

JOURNAL OF THE ASSOCIATION FOR INFORMATION SCIENCE AND TECHNOLOGY (2016)

添加到收藏夹

Article Construction & Building Technology

Integrated visualization for reinforced concrete using ultrasonic tomography and image-based 3-D reconstruction

Hajin Choi et al.

CONSTRUCTION AND BUILDING MATERIALS (2016)

添加到收藏夹

Article Computer Science, Information Systems

A fast and robust local descriptor for 3D point cloud registration

Jiaqi Yang et al.

INFORMATION SCIENCES (2016)

添加到收藏夹

Article Computer Science, Interdisciplinary Applications

Image-Based 3D Reconstruction for Posthurricane Residential Building Damage Assessment

Zixiang Zhou et al.

JOURNAL OF COMPUTING IN CIVIL ENGINEERING (2016)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Automated as-built 3D reconstruction of civil infrastructure using computer vision: Achievements, opportunities, and challenges

Habib Fathi et al.

ADVANCED ENGINEERING INFORMATICS (2015)

添加到收藏夹

Article Construction & Building Technology

Appearance-based material classification for monitoring of operation-level construction progress using 4D BIM and site photologs

Kevin K. Han et al.

AUTOMATION IN CONSTRUCTION (2015)

添加到收藏夹

Article Construction & Building Technology

Mapping actual thermal properties to building elements in gbXML-based BIM for reliable building energy performance modeling

Youngjib Ham et al.

AUTOMATION IN CONSTRUCTION (2015)

添加到收藏夹

Article Computer Science, Software Engineering

Denoising point sets via L0 minimization

Yujing Sun et al.

COMPUTER AIDED GEOMETRIC DESIGN (2015)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Kinect range sensing: Structured-light versus Time-of-Flight Kinect

Hamed Sarbolandi et al.

COMPUTER VISION AND IMAGE UNDERSTANDING (2015)

添加到收藏夹

Article Computer Science, Interdisciplinary Applications

Three-Dimensional Thermography-Based Method for Cost-Benefit Analysis of Energy Efficiency Building Envelope Retrofits

Youngjib Ham et al.

JOURNAL OF COMPUTING IN CIVIL ENGINEERING (2015)

添加到收藏夹

Article Computer Science, Interdisciplinary Applications

Generating Absolute-Scale Point Cloud Data of Built Infrastructure Scenes Using a Monocular Camera Setting

Abbas Rashidi et al.

JOURNAL OF COMPUTING IN CIVIL ENGINEERING (2015)

添加到收藏夹

Article Computer Science, Interdisciplinary Applications

Fully Automated As-Built 3D Pipeline Extraction Method from Laser-Scanned Data Based on Curvature Computation

Hyojoo Son et al.

JOURNAL OF COMPUTING IN CIVIL ENGINEERING (2015)

添加到收藏夹

Article Computer Science, Interdisciplinary Applications

Segmentation and Recognition of Highway Assets Using Image-Based 3D Point Clouds and Semantic Texton Forests

Mani Golparvar-Fard et al.

JOURNAL OF COMPUTING IN CIVIL ENGINEERING (2015)

添加到收藏夹

Article Computer Science, Interdisciplinary Applications

Automated Progress Monitoring Using Unordered Daily Construction Photographs and IFC-Based Building Information Models

Mani Golparvar-Fard et al.

JOURNAL OF COMPUTING IN CIVIL ENGINEERING (2015)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Vision-based material recognition for automated monitoring of construction progress and generating building information modeling from unordered site image collections

Andrey Dimitrov et al.

ADVANCED ENGINEERING INFORMATICS (2014)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Scalable Nearest Neighbor Algorithms for High Dimensional Data

Marius Muja et al.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2014)

添加到收藏夹

Article Computer Science, Interdisciplinary Applications

Image-Based Automated 3D Crack Detection for Post-disaster Building Assessment

Matthew M. Torok et al.

JOURNAL OF COMPUTING IN CIVIL ENGINEERING (2014)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Optimized selection of key frames for monocular videogrammetric surveying of civil infrastructure

Abbas Rashidi et al.

ADVANCED ENGINEERING INFORMATICS (2013)

添加到收藏夹

Article Computer Science, Artificial Intelligence

A videogrammetric as-built data collection method for digital fabrication of sheet metal roof panels

Habib Fathi et al.

ADVANCED ENGINEERING INFORMATICS (2013)

添加到收藏夹

Article Computer Science, Artificial Intelligence

An automated vision-based method for rapid 3D energy performance modeling of existing buildings using thermal and digital imagery

Youngjib Ham et al.

ADVANCED ENGINEERING INFORMATICS (2013)

添加到收藏夹

Article Construction & Building Technology

Skeleton-based 3D reconstruction of as-built pipelines from laser-scan data

Joohyuk Lee et al.

AUTOMATION IN CONSTRUCTION (2013)

添加到收藏夹

Article Construction & Building Technology

Image-based 3D scene reconstruction and exploration in augmented reality

Ming-Der Yang et al.

AUTOMATION IN CONSTRUCTION (2013)

添加到收藏夹

Article Construction & Building Technology

Comparison of Image-Based and Time-of-Flight-Based Technologies for Three-Dimensional Reconstruction of Infrastructure

Fei Dai et al.

JOURNAL OF CONSTRUCTION ENGINEERING AND MANAGEMENT (2013)

添加到收藏夹

Article Engineering, Civil

Precise Photogrammetric Reconstruction Using Model-Based Image Fitting for 3D Beam Deformation Monitoring

Eunju Kwak et al.

JOURNAL OF SURVEYING ENGINEERING (2013)

添加到收藏夹

Article Construction & Building Technology

Adaptive vision-based crack detection using 3D scene reconstruction for condition assessment of structures

Mohammad R. Jahanshahi et al.

AUTOMATION IN CONSTRUCTION (2012)

添加到收藏夹

Article Construction & Building Technology

Imaged-based verification of as-built documentation of operational buildings

Laura Klein et al.

AUTOMATION IN CONSTRUCTION (2012)

添加到收藏夹

Article Engineering, Electrical & Electronic

Lock-in Time-of-Flight (ToF) Cameras: A Survey

Sergi Foix et al.

IEEE SENSORS JOURNAL (2011)

添加到收藏夹

Article Computer Science, Software Engineering

Multi-Scale Geometry Interpolation

T. Winkler et al.

COMPUTER GRAPHICS FORUM (2010)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Accurate, Dense, and Robust Multiview Stereopsis

Yasutaka Furukawa et al.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2010)

添加到收藏夹

Article Computer Science, Information Systems

A quality controllable multi-view object reconstruction method for 3D imaging systems

Wen-Chao Chen et al.

JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION (2010)

添加到收藏夹

Article Computer Science, Information Systems

CiteSpace II: Detecting and visualizing emerging trends and transient patterns in scientific literature

CM Chen

JOURNAL OF THE AMERICAN SOCIETY FOR INFORMATION SCIENCE AND TECHNOLOGY (2006)

添加到收藏夹

Article Multidisciplinary Sciences

Coauthorship networks and patterns of scientific collaboration

MEJ Newman

PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA (2004)

添加到收藏夹

Image-based 3D reconstruction for Multi-Scale civil and infrastructure Projects: A review from 2012 to 2022 with new perspective from deep learning methods

相关参考文献

导出引文

分享论文