CuFusion2: Accurate and Denoised Volumetric 3D Object Reconstruction Using Depth Cameras

Zhang, Chen

doi:10.1109/access.2019.2911119

Cited by 8 publications

(2 citation statements)

References 52 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This proposed method improved the quality of the image and image resolution and it's more efficient in terms of computational speed. Chen Zhang [12] proposed a method for volumetric surface reconstruction and assumed that every scene consists of a cuboids structure.…”

Section: Related Workmentioning

confidence: 99%

Knowledge vector representation of three-dimensional convex polyhedrons and reconstruction of medical images using knowledge vector

Rani

Lakhwani

Kumar

2023

Multimed Tools Appl

View full text Add to dashboard Cite

Three-dimensional image construction and reconstruction play an important role in various applications of the real world in the field of computer vision. In the last three decades, researchers are continually working in this area because construction and reconstruction is an important approach in medical imaging. Reconstruction of the 3D image allows us to find the lesion information of the patients which could offer a new and accurate approach for the diagnosis of the disease and it adds a clinical value. Considering this, we proposed novel approaches for the construction and reconstruction of the image. First, the novel construction algorithm is used to extract the features from an image using syntactic pattern recognition. The proposed algorithm is able to extract in-depth features in all possible directions and planes and also able to represent the 3D image into a textual form. These features vector is nothing but a string that consists of direction and length information in syntactic form. For the identification of syntactic grammar, a real 3D clay model was made and identified the different possible patterns in the image. According to the domain knowledge, in a 3D image, a pixel could be present in 26 possible directions and we incorporated all possible directions in the proposed algorithm. In the same way, for the reconstruction of the image novel algorithm is proposed. In this algorithm, the knowledge vector has been taken as an input and the algorithm is able to reconstruct a 3D image.Reconstruction allows us to explore the internal details of the 3D images such as the size, shape, and structure of the object which could take us one step ahead in the field of medical image processing. Performances of the proposed algorithms are evaluated on five medical image dataset and the datasets are collected from Pentagram research institute, Hyderabad and results are outperformed in real-time. The accuracy of the proposed method is 94.78% and the average execution time is 6.76 seconds which is better than state of art methods.

show abstract

Section: Related Workmentioning

confidence: 99%

Knowledge vector representation of three-dimensional convex polyhedrons and reconstruction of medical images using knowledge vector

Rani

Lakhwani

Kumar

2023

Multimed Tools Appl

View full text Add to dashboard Cite

show abstract

“…Therefore, focusing solely on the RGB cameras is missing the potential that the RGB-D cameras may provide for the object reconstruction tasks. For example, depth data stream from the Kinect camera has been used to generate topologically correct 3D mesh models [39].…”

Section: Introductionmentioning

confidence: 99%

3D Object Reconstruction from Imperfect Depth Data Using Extended YOLOv3 Network

Kulikajevas

Maskeliūnas

Damaševičius

et al. 2020

Sensors

View full text Add to dashboard Cite

State-of-the-art intelligent versatile applications provoke the usage of full 3D, depth-based streams, especially in the scenarios of intelligent remote control and communications, where virtual and augmented reality will soon become outdated and are forecasted to be replaced by point cloud streams providing explorable 3D environments of communication and industrial data. One of the most novel approaches employed in modern object reconstruction methods is to use a priori knowledge of the objects that are being reconstructed. Our approach is different as we strive to reconstruct a 3D object within much more difficult scenarios of limited data availability. Data stream is often limited by insufficient depth camera coverage and, as a result, the objects are occluded and data is lost. Our proposed hybrid artificial neural network modifications have improved the reconstruction results by 8.53% which allows us for much more precise filling of occluded object sides and reduction of noise during the process. Furthermore, the addition of object segmentation masks and the individual object instance classification is a leap forward towards a general-purpose scene reconstruction as opposed to a single object reconstruction task due to the ability to mask out overlapping object instances and using only masked object area in the reconstruction process.

show abstract

Physical Environment Reconstruction Beyond Light Polarization for Coherent Augmented Reality Scene on Mobile Devices

Alhakamy

Tüceryan

2020

Transactions on Computational Science XXXVII

View full text Add to dashboard Cite

CuFusion2: Accurate and Denoised Volumetric 3D Object Reconstruction Using Depth Cameras

Cited by 8 publications

References 52 publications

Knowledge vector representation of three-dimensional convex polyhedrons and reconstruction of medical images using knowledge vector

Knowledge vector representation of three-dimensional convex polyhedrons and reconstruction of medical images using knowledge vector

3D Object Reconstruction from Imperfect Depth Data Using Extended YOLOv3 Network

Physical Environment Reconstruction Beyond Light Polarization for Coherent Augmented Reality Scene on Mobile Devices

Contact Info

Product

Resources

About