A Multi-view Stereo Benchmark with High-Resolution Images and Multi-camera Videos

Schöps, Thomas; Schönberger, Johannes L.; Galliani, Silvano; Sattler, Torsten; Schindler, Konrad; Pollefeys, Marc; Geiger, Andreas

doi:10.1109/cvpr.2017.272

Cited by 548 publications

(469 citation statements)

References 37 publications

Supporting

Mentioning

463

Contrasting

Unclassified

Order By: Relevance

“…To compensate for the lack of diversity in [42], [48], Jensen et al [16] published a number of real-world objects, which are still limited in the variety of scenes and viewpoints. Knapitsch et al [19] and Schops et al [41] provided the latest challenging datasets for indoor and outdoor scenes with high-resolution video data and 'ground truth' measurements obtained with a laser scanner, focusing on evaluating binocular stereo, multiview stereo, or structure-from-motion. Yet, their objects share the same limitation as those in earlier datasets, i.e, lacking diversity in both surface reflectance and viewpoints.…”

Section: Datasets For 3d Reconstructionmentioning

confidence: 99%

“…The 'ground truth' shape is available for quantitative evaluation. This 'DiLiGenT-MV' can be used to evaluate multi-view stereo methods (e.g., [41], [46]) under complex materials for lighting, be used to evaluate conventional single-view photometric stereo algorithms (e.g., [2], [45]) by treating each viewpoint independently. We quantitatively evaluate recent multi-view photometric stereo algorithms to further understand their pros and cons so as to encourage further research on unsolved issues.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Multi-View Photometric Stereo: A Robust Solution and Benchmark Dataset for Spatially Varying Isotropic Materials

Zhou

et al. 2020

IEEE Trans. on Image Process.

114

View full text Add to dashboard Cite

We present a method to capture both 3D shape and spatially varying reflectance with a multi-view photometric stereo (MVPS) technique that works for general isotropic materials. Our algorithm is suitable for perspective cameras and nearby point light sources. Our data capture setup is simple, which consists of only a digital camera, some LED lights, and an optional automatic turntable. From a single viewpoint, we use a set of photometric stereo images to identify surface points with the same distance to the camera. We collect this information from multiple viewpoints and combine it with structure-from-motion to obtain a precise reconstruction of the complete 3D shape. The spatially varying isotropic bidirectional reflectance distribution function (BRDF) is captured by simultaneously inferring a set of basis BRDFs and their mixing weights at each surface point. In experiments, we demonstrate our algorithm with two different setups: a studio setup for highest precision and a desktop setup for best usability. According to our experiments, under the studio setting, the captured shapes are accurate to 0.5 millimeters and the captured reflectance has a relative root-mean-square error (RMSE) of 9%. We also quantitatively evaluate state-of-the-art MVPS on a newly collected benchmark dataset, which is publicly available for inspiring future research.

show abstract

Section: Datasets For 3d Reconstructionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Multi-View Photometric Stereo: A Robust Solution and Benchmark Dataset for Spatially Varying Isotropic Materials

Zhou

et al. 2020

IEEE Trans. on Image Process.

114

View full text Add to dashboard Cite

show abstract

“…Due to its high accuracy and fine resolution, laser scanning has been used in many studies to produce high-quality ground truth reconstruction in which video sequences were used as input; the resulting point cloud was compared to the point cloud produced from a Faro scanner. Schöps et al (2017) also used a high-precision laser scanner to record the ground truth scene geometry for their benchmark. We took a similar approach in this study, using 3D data obtained from TLS as a reference to evaluate the data derived from the photogrammetric software.…”

Section: Recent Advancements In Computer Vision and Photogrammetrymentioning

confidence: 99%

Three‐dimensional digitization of the arid land plant Haloxylon ammodendron using a consumer‐grade camera

Huang

Zhang

Chen

et al. 2018

Ecology and Evolution

View full text Add to dashboard Cite

Plant structural parameters are important for ecological studies and for monitoring the environment. Terrestrial laser scanning has become a widely accepted technique for acquiring accurate high‐density three‐dimensional information about plant surfaces; however, this instrument is expensive, technically challenging to operate, heavy, and difficult to transport to hard‐to‐reach areas such as dense forests and undeveloped areas without easy vehicle access. Using Haloxylon ammodendron, a plant widely distributed in arid lands, as an example, we used a consumer‐grade handheld camera to take a series of overlapping images of this plant. Computer vision and photogrammetric software were used to reconstruct highly detailed three‐dimensional data of the plant surface. This surface data was compared to the point cloud of the plant acquired from concomitant terrestrial laser scanning. We demonstrated that the accuracy and degree of completeness of the image‐derived point clouds are comparable to that of laser scanning. Plant structural parameters (such as tree height and crown width) and three‐dimensional models extracted from the point clouds also agree well with a relative difference of less than 5%. Our case study shows that a common camera and image processing software can be an affordable, highly portable, and viable option for acquiring accurate and detailed high‐density and high‐resolution three‐dimensional information about plant structure in the environment. This digitization technique can record the plant and its surrounding environment effectively and efficiently, and it can be applied to many ecological fields and studies.

show abstract

“…Nevertheless, recent work by Schöps et al. () and Knapitsch et al. () have presented some 3D reconstruction benchmarks, including both outdoor scenes and indoor environments, that provide very good results in terms of completeness and accuracy.…”

Section: Introductionmentioning

confidence: 99%

GRAPHOS – open‐source software for photogrammetric applications

Aguilera

López-Fernández

Rodríguez‐Gonzálvez

et al. 2018

The Photogrammetric Record

View full text Add to dashboard Cite

This paper reports the latest developments for the photogrammetric open‐source tool called GRAPHOS (inteGRAted PHOtogrammetric Suite). GRAPHOS includes some recent innovations in the image‐based 3D reconstruction pipeline, from automatic feature detection/description and network orientation to dense image matching and quality control. GRAPHOS also has a strong educational component beyond its automated processing functions, reinforced with tutorials and didactic explanations about algorithms and performance. The paper highlights recent developments carried out at different levels: graphical user interface (GUI), didactic simulators for image processing, photogrammetric processing with weight parameters, dataset creation and system evaluation.

show abstract

A Multi-view Stereo Benchmark with High-Resolution Images and Multi-camera Videos

Cited by 548 publications

References 37 publications

Multi-View Photometric Stereo: A Robust Solution and Benchmark Dataset for Spatially Varying Isotropic Materials

Multi-View Photometric Stereo: A Robust Solution and Benchmark Dataset for Spatially Varying Isotropic Materials

Three‐dimensional digitization of the arid land plant Haloxylon ammodendron using a consumer‐grade camera

GRAPHOS – open‐source software for photogrammetric applications

Contact Info

Product

Resources

About