Overview of 3D Reconstruction Methods Based on Multi-view

Li, Mengxin; Dai, Zheng; Zhang, Rui; Yin, Jiadi; Tian, Xiangqian

doi:10.1109/ihmsc.2015.117

Cited by 4 publications

(4 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Here, we only highlight the most relevant methods with respect to our proposed models. For a more detailed overview see for 3D reconstruction (Li et al, 2015) and image generation (Zhu et al, 2017b).…”

Section: Related Workmentioning

confidence: 99%

IterGANs: Iterative GANs to learn and control 3D object transformation

Galama

Mensink²

2019

Computer Vision and Image Understanding

View full text Add to dashboard Cite

We are interested in learning visual representations which allow for 3D manipulations of visual objects based on a single 2D image. We cast this into an image-to-image transformation task, and propose Iterative Generative Adversarial Networks (IterGANs) which iteratively transform an input image into an output image. Our models learn a visual representation that can be used for objects seen in training, but also for never seen objects. Since object manipulation requires a full understanding of the geometry and appearance of the object, our IterGANs learn an implicit 3D model and a full appearance model of the object, which are both inferred from a single (test) image. Two advantages of IterGANs are that the intermediate generated images can be used for an additional supervision signal, even in an unsupervised fashion, and that the number of iterations can be used as a control signal to steer the transformation. Experiments on rotated objects and scenes show how IterGANs help with the generation process.

show abstract

Section: Related Workmentioning

confidence: 99%

IterGANs: Iterative GANs to learn and control 3D object transformation

Galama

Mensink²

2019

Computer Vision and Image Understanding

View full text Add to dashboard Cite

show abstract

“…The acquisition of multiview images has attracted much attention as an important approach to 3D imaging with a wide FOV and a rich point cloud. [4][5][6] For 3D imaging systems based on camera arrays, An et al 7 developed a sparse imaging method from array camera images and a super-resolution approach for narrowly spaced objects. Ruiz et al 8 proposed a reliable multicamera sensor array-based 3D target imaging approach.…”

Section: Introductionmentioning

confidence: 99%

“…Many innovative imaging systems have been developed to enhance 3D imaging performance, such as camera arrays, camera motion, and the addition of other optical imaging elements. The acquisition of multiview images has attracted much attention as an important approach to 3D imaging with a wide FOV and a rich point cloud 4 – 6 For 3D imaging systems based on camera arrays, An et al 7 .…”

Section: Introductionmentioning

confidence: 99%

Large-field-of-view three-dimensional imaging from multiple virtual views

Li,

Wan,

et al. 2024

Opt. Eng.

View full text Add to dashboard Cite

We present a virtual multiview imaging method that incorporates a pair of Risley prisms and a stationary camera coaxially mounted. By rotating double Risley prisms, the virtual array camera (VAC) is generated to capture multiframe images from different perspectives for three-dimensional (3D) reconstruction, which not only extends the field of view (FOV) but also generates rich point cloud data. The VAC imaging process, including the virtual camera imaging theoretical model, automatic virtual optical center calibration, point cloud data acquisition, and target pose estimation, is developed to enable virtual camera field construction. Moreover, an improved iterative closest point registration algorithm by combining the overlapping prepositioning method is proposed to improve the speed of multiframe point cloud stitching. The experiments on real data validate the feasibility and flexibility of our 3D imaging technique capable of realizing large-FOV 3D imaging and accurate pose estimation of the target, which demonstrates a promising application prospect in visual imaging fields.

show abstract

“…Snavely et al [12] encountered many issues when working with photo tourism, restoring images of historic locations that people had photographed under various conditions using the SfM method. Li et al [13] briefly introduced and summarized an algorithm for multi-image 3D reconstruction. Remondino et al [14] compared the results of dense image matching algorithms (SURE, Micmac, PMVS, Photoscan) with various data sets captured using a DSLR camera.…”

Section: Introductionmentioning

confidence: 99%

High-Resolution 3D Crop Reconstruction and Automatic Analysis of Phenotyping Index Using Machine Learning

Yang

Cho

2021

Agriculture

View full text Add to dashboard Cite

Beyond the use of 2D images, the analysis of 3D images is also necessary for analyzing the phenomics of crop plants. In this study, we configured a system and implemented an algorithm for the 3D image reconstruction of red pepper plant (Capsicum annuum L.), as well as its automatic analysis. A Kinect v2 with a depth sensor and a high-resolution RGB camera were used to obtain more accurate reconstructed 3D images. The reconstructed 3D images were compared with conventional reconstructed images, and the data of the reconstructed images were analyzed with respect to their directly measured features and accuracy, such as leaf number, width, and plant height. Several algorithms for image extraction and segmentation were applied for automatic analysis. The results showed that the proposed method showed an error of about 5 mm or less when reconstructing and analyzing 3D images, and was suitable for phenotypic analysis. The images and analysis algorithms obtained by the 3D reconstruction method are expected to be applied to various image processing studies.

show abstract

Overview of 3D Reconstruction Methods Based on Multi-view

Cited by 4 publications

References 27 publications

IterGANs: Iterative GANs to learn and control 3D object transformation

IterGANs: Iterative GANs to learn and control 3D object transformation

Large-field-of-view three-dimensional imaging from multiple virtual views

High-Resolution 3D Crop Reconstruction and Automatic Analysis of Phenotyping Index Using Machine Learning

Contact Info

Product

Resources

About