Improved Depth Image-Based Rendering Using an Adaptive Compensation Method on an Autostereoscopic 3-D Display for a Kinect Sensor

Hsia, Chih-Hsien

doi:10.1109/jsen.2014.2359225

Cited by 21 publications

(2 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, due to occlusion in the scene, the composite image usually contains holes. Some scholars have proposed to make adaptive compensation for the missing information in the depth map and use a Gaussian filter to reduce holes [11]. Some scholars have proposed a method of synthesizing new viewpoints from images of multiple viewpoints to minimize holes and use oversampling to compensate for the existing image missing [12].…”

Section: B Image-based Renderingmentioning

confidence: 99%

Real-Time High Realistic Web Display Method of Complex 3D Model

et al. 2021

View full text Add to dashboard Cite

With the in-depth application of 3D models in many fields, the display of models, especially the model display based on B / S architecture, has become an indispensable part of the application of 3D models. The development of 3D modeling technology has led to the emergence of a large number of complex three-dimensional models with more than one hundred thousand facets and hundred megabytes of file size. Coupled with the limit of B / S architecture by the server's concurrency, network bandwidth, browser's processing capabilities, and many other objective factors, how to achieve its real-time and high-realistic display on the web pages has become one of the hot spots research in the field of graphics, which has great research significance and challenge. In order to resolve the above problems, we propose a new model display method. The method pre-renders the model into a two-dimensional image by sampling the subdivide surface of the model's circumscribed sphere and uses the view-dependent level-of-detail method to divide the pre-rendered image into different layers and tiles. Combined with the optimization, including adaptive and progressive network transmission, index-weighted user interaction prediction, and Hilbert-based image indexing, the method achieves a frame rate of more than 20 frames per second in the actual tests.

show abstract

Section: B Image-based Renderingmentioning

confidence: 99%

Real-Time High Realistic Web Display Method of Complex 3D Model

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Improved depth image-based rendering is used an adaptive compensation method on an autostereoscopic 3d display for a kinect sensor by chih hsien et al [12]. Din-Yuen Chan proposed kinect based stereo matching method to be used of the improved depth sequence.…”

Section: Related Workmentioning

confidence: 99%

Real Time Depth Data Refurbishment in Frequency Domain and 3D Modeling Map Using Microsoft Kinect Sensor

Raviya¹,

Vyas²,

Kothari³

2016

IJIGSP

View full text Add to dashboard Cite

The present decade has seen the growth of both, the software and hardware for three dimensional televisions in real time applications. Depth map is fundamental key of 3-Dimensional algorithms. Reliable depth map is an acceptance in 3D transmission, analysis and compression of algorithm. Computer vision and pattern recognition research fields use sensor like low cost Microsoft kinect. Kinect sensor suffers from some problems of noise, poor accuracy and unmatched edges. This paper presents effective solution to improve the real time depth sequences and real time 3-D map using warping method from kinect sensor. We proposed real time frequency domain based depth data refurbishment and improve the quality of depth video provided by sensors' Microsoft Kinect. The quality of the depth map is improved by depth refurbishment in frequency domain technique, filling the holes present in the maps, 2-Dimensional spatial filtering and permutation of morphological operation. We show that the proposed approach is able to generate high quality depth maps which can be quite useful in improving the performance of various applications of Microsoft Kinect such as obstacle detection and avoidance, pose estimation, gesture recognition, skeletal and facial tracking, etc. We produce the real time 3-D map using warping method. An experimental result shows that the quality of our proposed method is better than previous research works. Our algorithm produces noise less, reliable, smooth and efficient depth sequence. The qualitative parameter Peak Signal to Noise Ratio (PSNR), Structure Similarity Index Map (SSIM) and Mean Square Error (MSE) measure the real time results for comparative analysis.

show abstract

Real-time ultra-high definition multiview glasses-free 3D display system

Liu

Zhang

et al. 2018

Vis Comput

View full text Add to dashboard Cite

Improved Depth Image-Based Rendering Using an Adaptive Compensation Method on an Autostereoscopic 3-D Display for a Kinect Sensor

Cited by 21 publications

References 22 publications

Real-Time High Realistic Web Display Method of Complex 3D Model

Real-Time High Realistic Web Display Method of Complex 3D Model

Real Time Depth Data Refurbishment in Frequency Domain and 3D Modeling Map Using Microsoft Kinect Sensor

Real-time ultra-high definition multiview glasses-free 3D display system

Contact Info

Product

Resources

About