Let There Be Color! Large-Scale Texturing of 3D Reconstructions

Waechter, Michael; Moehrle, Nils; Goesele, Michael

doi:10.1007/978-3-319-10602-1_54

Cited by 281 publications

(235 citation statements)

References 21 publications

Supporting

Mentioning

219

Contrasting

Unclassified

Order By: Relevance

“…The colour from the original image was then incorporated into the model to get a textured output (Figure 21). The texturing of the 3D surface 24,25 mesh was very important for generating an aesthetically pleasing and realistic 3D model for visualization. The result of the texturing depends on the resolution of original input images and quality of mesh geometry.…”

Section: Meshing and Texturingmentioning

confidence: 99%

See 1 more Smart Citation

Towards Generation of Effective 3D Surface Models from UAV Imagery Using Open Source Tools

et al. 2018

View full text Add to dashboard Cite

There has been increasing popularity in large scale mapping for deriving 3D surface and elevation models of earth and building structures. The techniques of computer vision comprising feature detections and matching and photogrammetry play an important role in deriving near accurate 3D reconstruction of scenes from 2D images. Since the images captured by the unmanned aerial vehicle (UAVs) are of high resolution, there is need for more sophisticated processing and analysis of the imagery to generate 3D models and other useful imagery products. The open source softwares are excellent tools for research and can be modified or changed to suit our model, as specific or combinations of algorithms behave differently based on the nature of UAV image scene to be processed. Though many algorithms are available for performing feature extractions from images, few studies have been carried out to identify suitable detector algorithms to be used based on the nature of image or scene that the UAV captures. An attempt has been made to understand and analyse the suitability of feature detection and descriptor algorithms for different scene types. This article also describes the popular technique called structure from motion process pipeline for sequential processing of UAV images with high overlapping, which involves the estimation of 3D point clouds from the keypoint correspondences. The relative accuracy of the 3D point cloud derived from our approach is comparable with similar output from other state-of-the-art UAV processing systems and is found to match with high precision.

show abstract

Section: Meshing and Texturingmentioning

confidence: 99%

“…Then, texturing was done through a multi-view approach. Therefore a combined approach with SfM and MVS techniques having large number of input images and mesh geometry consisting of thousands of triangles in a reasonable time 26 was considered an effective technique for efficient texturing process.…”

Section: Meshing and Texturingmentioning

confidence: 99%

Towards Generation of Effective 3D Surface Models from UAV Imagery Using Open Source Tools

et al. 2018

View full text Add to dashboard Cite

show abstract

“…A mixed silhouette-based and photo-consistent 3D reconstruction approach [70] was executed with a set of silhouette images segmented by the level set method [71]. The point cloud was constructed into mesh format using the Poisson method [72], and then, the mesh is textured with the color images [73]. Considerable indoor 3D reconstruction results are shown in Figures 19 and 20 (the images also captured from 1080p video).…”

Section: D Reconstruction Applicationmentioning

confidence: 99%

Automatic Pose Estimation of Uncalibrated Multi-View Images Based on a Planar Object with a Predefined Contour Model

Zhou

Wen-he

2016

IJGI

View full text Add to dashboard Cite

Abstract:We have presented a framework to obtain camera pose (i.e., position and orientation in the 3D space) with real scale information of the uncalibrated multi-view images and the intrinsic camera parameters automatically. Our framework consists of two key steps. First, the initial value of the intrinsic camera and the pose parameters were extracted from homography estimation based on the contour model of some planar objects. Second, a refinement of the intrinsic camera and pose parameters was operated by the bundle adjustment procedure. Our framework can provide a complete flow of pose estimation of disorderly or orderly uncalibrated multi-view images, which can be used in vision tasks requiring scale information. Real multi-view images were utilized to demonstrate the robustness, flexibility and accuracy of the proposed framework. The proposed framework was also applied in 3D reconstruction.

show abstract

“…The method produces watertight triangle meshes from unstructured point clouds very robustly even in the presence of noise and gross outliers in the raw 3D sample points. The meshes can then be textured (Waechter et al, 2014) from the input images to generate a photorealistic representation of the scene.…”

Section: Surface Reconstruction and Texturingmentioning

confidence: 99%

On the Use of Uavs in Mining and Archaeology - Geo-Accurate 3d Reconstructions Using Various Platforms and Terrestrial Views

Tscharf

Rumpler

Fraundorfer

et al. 2015

ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

ABSTRACT:During the last decades photogrammetric computer vision systems have been well established in scientific and commercial applications. Especially the increasing affordability of unmanned aerial vehicles (UAVs) in conjunction with automated multi-view processing pipelines have resulted in an easy way of acquiring spatial data and creating realistic and accurate 3D models. With the use of multicopter UAVs, it is possible to record highly overlapping images from almost terrestrial camera positions to oblique and nadir aerial images due to the ability to navigate slowly, hover and capture images at nearly any possible position. Multi-copter UAVs thus are bridging the gap between terrestrial and traditional aerial image acquisition and are therefore ideally suited to enable easy and safe data collection and inspection tasks in complex or hazardous environments. In this paper we present a fully automated processing pipeline for precise, metric and geo-accurate 3D reconstructions of complex geometries using various imaging platforms. Our workflow allows for georeferencing of UAV imagery based on GPS-measurements of camera stations from an on-board GPS receiver as well as tie and control point information. Ground control points (GCPs) are integrated directly in the bundle adjustment to refine the georegistration and correct for systematic distortions of the image block. We discuss our approach based on three different case studies for applications in mining and archaeology and present several accuracy related analyses investigating georegistration, camera network configuration and ground sampling distance. Our approach is furthermore suited for seamlessly matching and integrating images from different view points and cameras (aerial and terrestrial as well as inside views) into one single reconstruction. Together with aerial images from a UAV, we are able to enrich 3D models by combining terrestrial images as well inside views of an object by joint image processing to generate highly detailed, accurate and complete reconstructions.

show abstract

Let There Be Color! Large-Scale Texturing of 3D Reconstructions

Cited by 281 publications

References 21 publications

Towards Generation of Effective 3D Surface Models from UAV Imagery Using Open Source Tools

Towards Generation of Effective 3D Surface Models from UAV Imagery Using Open Source Tools

Automatic Pose Estimation of Uncalibrated Multi-View Images Based on a Planar Object with a Predefined Contour Model

On the Use of Uavs in Mining and Archaeology - Geo-Accurate 3d Reconstructions Using Various Platforms and Terrestrial Views

Contact Info

Product

Resources

About