4.7 Article

DP-MVS: Detail Preserving Multi-View Surface Reconstruction of Large-Scale Scenes

Related references

Note: Only part of the references are listed.
Article Environmental Sciences

Use of SfM-MVS approach to nadir and oblique images generated throught aerial cameras to build 2.5D map and 3D models in urban areas

Massimiliano Pepe et al.

Summary: The use of Structure-from-Motion (SfM) and Multi-View-Stereo (MVS) approaches for constructing 3D models of Cultural Heritage structures is becoming more popular. However, the use of aerial images generated by airborne sensors in the SfM-MVS approach has been limited due to computation problems and poor geometric acquisition. With advancements in image acquisition and technology, it is now possible to obtain higher-quality city models using SfM/MVS approach.

GEOCARTO INTERNATIONAL (2022)

Article Computer Science, Software Engineering

Aerial Path Planning for Online Real-Time Exploration and Offline High-Quality Reconstruction of Large-Scale Urban Scenes

Yilin Liu et al.

Summary: The study introduces a real-time explore-and-reconstruct planning algorithm that can reconstruct 3D models of urban environments without prior knowledge of scene geometry, reducing reconstruction costs and simplifying the operation process.

ACM TRANSACTIONS ON GRAPHICS (2021)

Article Environmental Sciences

Sampling-Based Path Planning for High-Quality Aerial 3D Reconstruction of Urban Scenes

Feihu Yan et al.

Summary: This study proposes a novel path planning method for high-quality aerial 3D reconstruction of urban scenes, which involves capturing aerial photos to generate a coarse 3D model, evaluating and generating optimized paths. Experimental results suggest a significant improvement in the performance of aerial 3D urban reconstruction using the proposed method.

REMOTE SENSING (2021)

Article Environmental Sciences

Semantically Derived Geometric Constraints for MVS Reconstruction of Textureless Areas

Elisavet Konstantina Stathopoulou et al.

Summary: A novel approach is proposed to increase confidence and support depth and normal map estimation by leveraging semantic priors into a PatchMatch-based MVS. During depth estimation optimization, class-specific geometric constraints are imposed using semantic class labels on image pixels.

REMOTE SENSING (2021)

Article Environmental Sciences

A Practical 3D Reconstruction Method for Weak Texture Scenes

Xuyuan Yang et al.

Summary: In recent years, there has been a growing demand for 3D reconstructions of tunnel pits, underground pipe networks, and building interiors. To address the issue of weak or repeated textures in these scenarios, researchers proposed covering lighting sources with films of spark patterns to add textures, and combined deep learning algorithms with traditional methods to improve the effectiveness of the reconstruction. The experiments have verified the feasibility and efficiency of the proposed method.

REMOTE SENSING (2021)

Article Computer Science, Software Engineering

Mobile3DRecon: Real-time Monocular 3D Reconstruction on a Mobile Phone

Xingbin Yang et al.

IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS (2020)

Article Computer Science, Artificial Intelligence

Mesh-based camera pairs selection and occlusion-aware masking for mesh refinement

Andrea Romanoni et al.

PATTERN RECOGNITION LETTERS (2019)

Article Computer Science, Software Engineering

Joint bilateral propagation upsampling for unstructured multi-view stereo

Mengqiang Wei et al.

VISUAL COMPUTER (2019)

Article Geography, Physical

Prioritized multi-view stereo depth map generation using confidence prediction

Christian Mostegel et al.

ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING (2018)

Article Computer Science, Artificial Intelligence

Accurate Multiple View 3D Reconstruction Using Patch-Based Stereo for Large-Scale Scenes

Shuhan Shen

IEEE TRANSACTIONS ON IMAGE PROCESSING (2013)

Article Computer Science, Artificial Intelligence

High Accuracy and Visibility-Consistent Dense Multiview Stereo

Hoang-Hiep Vu et al.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2012)

Article Computer Science, Artificial Intelligence

Efficient large-scale multi-view stereo for ultra high-resolution image sets

Engin Tola et al.

MACHINE VISION AND APPLICATIONS (2012)

Article Computer Science, Artificial Intelligence

Multiview Stereo and Silhouette Consistency via Convex Functionals over Convex Domains

Daniel Cremers et al.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2011)

Article Computer Science, Artificial Intelligence

DAISY: An Efficient Dense Descriptor Applied to Wide-Baseline Stereo

Engin Tola et al.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2010)

Article Computer Science, Artificial Intelligence

Accurate, Dense, and Robust Multiview Stereopsis

Yasutaka Furukawa et al.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2010)

Article Computer Science, Software Engineering

PatchMatch: A Randomized Correspondence Algorithm for Structural Image Editing

Connelly Barnes et al.

ACM TRANSACTIONS ON GRAPHICS (2009)

Article Computer Science, Software Engineering

Robust and Efficient Surface Reconstruction From Range Data

P. Labatut et al.

COMPUTER GRAPHICS FORUM (2009)

Article Computer Science, Artificial Intelligence

Multiview stereo via volumetric graph-cuts and occlusion robust photo-consistency

George Vogiatzis et al.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2007)

Article Computer Science, Artificial Intelligence

A quasi-dense approach to surface reconstruction from uncalibrated images

M Lhuillier et al.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2005)

Article Computer Science, Artificial Intelligence

Silhouette and stereo fusion for 3D object modeling

CH Esteban et al.

COMPUTER VISION AND IMAGE UNDERSTANDING (2004)