A number of high-quality depth imaged-based rendering (DIBR) pipelines have been developed to reconstruct a 3D scene from several images taken from known camera viewpoints. Due to the specific limitations of each technique, their output is prone to artifacts. Therefore the quality cannot be ensured. To improve the quality of the most critical and challenging image areas, an exhaustive comparison is required. In this paper, we consider three questions of benchmarking the quality performance of eight DIBR techniques on light fields: First, how does the density of original input views affect the quality of the rendered novel views? Second, how does disparity range between adjacent input views impact the quality? Third, how does each technique behave for different object properties? We compared and evaluated the results visually as well as quantitatively (PSNR, SSIM, AD, and VDP2). The results show some techniques outperform others in different disparity ranges. The results also indicate using more views not necessarily results in visually higher quality for all critical image areas. Finally we have shown a comparison for different scene's complexity such as non-Lambertian objects.
Access to the published version may require subscription. N.B. When citing this work, cite the original published paper. Copyright (2020) Society of Photo Optical Instrumentation Engineers (SPIE). One print or electronic copy may be made for personal use only. Systematic reproduction and distribution, duplication of any material in this publication for a fee or for commercial purposes, and modification of the contents of the publication are prohibited.
Light-field imaging provides full spatio-angular information of the real world by capturing the light rays in various directions. This allows image processing algorithms to result in immersive user experiences such as VR. To evaluate, and develop reconstruction algorithms, a precise and dense light-field dataset of the real world that can be used as ground truth is desirable. In this paper, a nonplanar capture is done and a view rendering pipeline is implemented. The acquired dataset includes two scenes that are captured by an accurate industrial robot with an attached color camera such that the camera is looking outward. The arm moves on a cylindrical path for a field of view of 125 degrees with angular step size of 0.01 degrees. Both scenes and their corresponding geometric calibration parameters will be available with the publication of the paper. The images are pre-processed in different steps. The disparity between two adjacent views with resolution of 5168𝑥3448 is less than 1.6 pixels; the parallax between the foreground and the background objects is less than 0.6 pixels. Furthermore, the pre-processed data is used for a view rendering experiment to demonstrate an exemplary use case. In addition, the rendered results are evaluated visually and objectively.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.