Related references
Note: Only part of the references are listed.
Article
Geography, Physical
Elisavet Konstantina Stathopoulou et al.
Summary: To support depth estimation in challenging surfaces scenarios, we propose an extended PatchMatch pipeline using an adaptive accumulated matching cost calculation. Our approach achieves competitive results compared to state-of-the-art methods by favoring the reconstruction of problematic regions while preserving fine details in rich textured regions.
ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING
(2023)
Article
Geography, Physical
Jingxue Wang et al.
Summary: This study proposes a dynamic programming stereo-matching method based on the minimum spanning tree (MST). By obtaining stable initial cost values, constructing pixel- and region-level MSTs, and re-deducing the cost-aggregation process using dynamic programming, a high-precision smooth disparity map is obtained. Experimental results demonstrate the effectiveness of the proposed method in improving the accuracy of stereo-matching.
PHOTOGRAMMETRIC RECORD
(2023)
Article
Geography, Physical
Shiqing Wei et al.
Summary: This paper proposes an end-to-end learnable framework called BuildMapper for building contour extraction. It can directly and efficiently delineate building polygons without complex empirical post-processing. With the introduction of new methods and techniques in two components, the framework achieves state-of-the-art performance in building contour extraction.
ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING
(2023)
Article
Computer Science, Artificial Intelligence
Xuedian Zhang et al.
Summary: In this paper, a Multiple Granularities Feature Fusion Network for Multi-View Stereo is proposed to improve the quality and completeness of model reconstruction. The network combines global and local features through fine-granularity multi-feature fusion, and uses distributed 3D convolution to reduce memory consumption. Experimental results show that the proposed method achieves state-of-the-art performance in accuracy and effectiveness.
Article
Geography, Physical
Corinne Stucker et al.
Summary: This article introduces a convolutional neural network-based stereo matching method that learns geometric priors from example data to optimize and complement the initial stereo results. The proposed method consistently improves the quantitative and qualitative performance of stereo DSMs, and it can generalize to different regions and cities with a certain degree of invariance.
ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING
(2022)
Article
Geography, Physical
Minye Wang et al.
Summary: This paper presents a new method for reconstructing traffic sign point clouds based on panoramic images. The method extracts traffic sign point clouds using arc feature and spatial semantic feature analysis, detects traffic signs in images using color and shape features as well as a convolutional neural network, registers the traffic sign point cloud and images based on outline features, and finally matches traffic sign points with traffic sign pixels to reconstruct the traffic sign point cloud.
PHOTOGRAMMETRIC RECORD
(2022)
Article
Computer Science, Software Engineering
Shang Sun et al.
Summary: This paper proposes a PatchMatch-based multi-view stereo (MVS) algorithm that has achieved success in large-scale scene reconstruction tasks. However, reconstruction of textureless planes often fails, so a potential depth hypothesis inference strategy is proposed to improve the completeness of the reconstruction result. In addition, a new acceleration scheme is proposed to speed up the depth map estimation process. The proposed method, PHI-MVS, demonstrates competing performance against the state-of-the-art on benchmark datasets.
COMPUTERS & GRAPHICS-UK
(2022)
Article
Geography, Physical
Cailin Li et al.
Summary: Unmanned aerial vehicle inspection of vegetation or other obstacles in power transmission line corridors is an economical and efficient method. The proposed method uses the vertical plane constraint to restore the spatial position of the power line, and it can effectively detect obstacles around the power line.
PHOTOGRAMMETRIC RECORD
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Stefano Zorzi et al.
Summary: This paper introduces PolyWorld, a neural network that directly extracts building vertices from an image and connects them correctly to create precise polygons. The model predicts the connection strength between each pair of vertices using a graph neural network and estimates the assignments by solving a differentiable optimal transport problem. PolyWorld significantly outperforms the state of the art in building polygonization and achieves visually pleasing results in creating building polygons.
2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022)
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Yikang Ding et al.
Summary: This paper introduces TransMVSNet, which leverages feature matching Transformer and other techniques to achieve state-of-the-art performance in multi-view stereo matching.
2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)
(2022)
Article
Geography, Physical
Minye Wang et al.
Summary: This paper introduces a new method for reconstructing vertical rectangle traffic sign point clouds based on panoramic images, by extracting traffic sign point clouds using arc feature and spatial semantic features analysis, detecting traffic signs in images through colour and shape features and a convolutional neural network. Ultimately, the proposed method effectively achieves colourful, high-resolution and complete traffic sign point cloud reconstruction.
PHOTOGRAMMETRIC RECORD
(2022)
Article
Geography, Physical
Dawen Yu et al.
Summary: The study introduces a new fully automatic three-dimensional building reconstruction method that can generate first level of detail building models from multi-view aerial images. It consists of efficient dense matching and Earth surface reconstruction, reliable building footprint extraction and polygon regularization, and highly accurate height inference of building roofs and bases. The method utilized deep learning-based multi-view matching, deep-learning based segmentation, and novel height inference techniques to achieve results exceeding other similar methods.
ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING
(2021)
Article
Computer Science, Hardware & Architecture
Xiang Wang et al.
Summary: This paper provides a comprehensive review on recent deep learning methods for multi-view stereo, categorizing them into depth map based and volumetric based methods. It reviews representative methods in detail and summarizes widely used datasets and metrics for evaluation, while also presenting insightful observations and challenges for future research directions.
Article
Geography, Physical
Anzhu Yu et al.
Summary: Our proposed approach introduces a coarse-to-fine depth inference strategy to achieve high resolution depth maps, and experimental results on multiple datasets show that our method outperforms most existing methods.
ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING
(2021)
Article
Computer Science, Information Systems
Penglei Ji et al.
Summary: This paper introduces a continuous stereo disparity estimation method based on superpixel segmentation and graph-cuts. By re-parameterizing the disparity with a 3D tangent plane and proposing two optimization algorithms for the Markov Random Field (MRF) energy, the method achieves high accuracy on evaluation benchmarks.
JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION
(2021)
Article
Geography, Physical
Emmanuel Moisan et al.
Summary: This paper presents an original method for 3D modelling of navigable tunnel tubes using dynamic data acquired from a boat, utilizing photogrammetry and multibeam echo sounder. The accuracy of the method is centimetric for vaults and decimetric for underwater features, as demonstrated through comparison with reference models obtained from static laser and sonar acquisitions.
PHOTOGRAMMETRIC RECORD
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Francois Darmon et al.
Summary: This study examines the effectiveness of deep multi-view stereo methods when utilizing internet photo collections. Results show issues with unsupervised training on wild data, but supervised deep depthmap-based MVS methods perform exceptionally well in reconstructing a small number of internet images.
2021 INTERNATIONAL CONFERENCE ON 3D VISION (3DV 2021)
(2021)
Article
Geography, Physical
Emmanuel Moisan et al.
Summary: This paper introduces an original method for modelling in 3D the full tube of navigable tunnels using data acquired dynamically from a boat. The method combines photogrammetry and sonar profiles to reconstruct the tunnel vault and estimate the trajectory of the vessel, showing high accuracy in the reconstruction of the vault.
PHOTOGRAMMETRIC RECORD
(2021)
Article
Geography, Physical
Xu Huang et al.
PHOTOGRAMMETRIC RECORD
(2020)
Proceedings Paper
Computer Science, Artificial Intelligence
Keyang Luo et al.
2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)
(2020)
Article
Computer Science, Artificial Intelligence
Po-Heng Chen et al.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2020)
Article
Engineering, Electrical & Electronic
Rongjun Qin et al.
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
(2019)
Article
Geography, Physical
Lei Ye et al.
PHOTOGRAMMETRIC ENGINEERING AND REMOTE SENSING
(2018)
Article
Computer Science, Software Engineering
Arno Knapitsch et al.
ACM TRANSACTIONS ON GRAPHICS
(2017)
Proceedings Paper
Computer Science, Artificial Intelligence
Jifeng Dai et al.
2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV)
(2017)
Article
Geography, Physical
Han Hu et al.
ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING
(2016)
Article
Environmental Sciences
Xiao Ling et al.
Article
Computer Science, Software Engineering
Yannick Verdie et al.
ACM TRANSACTIONS ON GRAPHICS
(2015)
Article
Geography, Physical
Han Hu et al.
PHOTOGRAMMETRIC ENGINEERING AND REMOTE SENSING
(2015)
Article
Geography, Physical
Fabio Remondino et al.
PHOTOGRAMMETRIC RECORD
(2014)
Article
Computer Science, Software Engineering
Michael Kazhdan et al.
ACM TRANSACTIONS ON GRAPHICS
(2013)
Article
Computer Science, Artificial Intelligence
Hoang-Hiep Vu et al.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2012)
Article
Geography, Physical
Bo Wu et al.
ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING
(2012)
Article
Computer Science, Artificial Intelligence
Yasutaka Furukawa et al.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2010)
Article
Geography, Physical
L Zhang et al.
ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING
(2006)
