Virtual view synthesis through linear processing without geometry

Kubota, Akira; Aizawa, Kiyoharu; Chen, T.

doi:10.1109/icip.2004.1421746

Cited by 3 publications

(6 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The presented approach is much efficient compared with the previous method. A comparison between the proposed filtering approach and the multilayered rendering and fusion method [4]. In this paper, we show that similar results as the multi-layered rendering and fusion approach can be obtained by directly filtering the captured images.…”

Section: Introductionsupporting

confidence: 58%

“…2 (b), the multi-layered rendering and fusing method [4] consists of two steps. In the first step, two virtual images, g 1 and g 2 , are generated at the center point of the camera array by using the conventional LFR method based on two depths, z 1 and z 2 , respectively.…”

Section: B Image Formation Model In the Multi-layered Rendering And mentioning

confidence: 99%

“…The reconstruction filter r i is derived by integrating all the processing steps in the multi-layered rendering and fusing method ( Fig. 2 (b)) , which is our previously proposed method [4].…”

Section: A Problem Formulationmentioning

confidence: 99%

“…Our goal is to generate an image of a novel view at the center of the camera array by directly filtering the captured images. The reconstruction filter is derived through integration of all steps of our previously presented method [4] into a one-shot process. The previous method is composed of Camera 1 Virtual camera Fig.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Direct filtering method for image based rendering

Kubota

Aizawa

Chen

2005

IEEE International Conference on Image Processing 2005

Self Cite

View full text Add to dashboard Cite

Image based rendering (IBR) is basically a light ray resampling method for generating a novel image without aliasing artifacts from a given set of sampled light rays. To avoid aliasing artifacts, conventional methods require an estimate of the scene geometry. In this paper, we present a novel IBR method by linear filtering without estimating the scene geometry, for the simplified case when generating a virtual image at the center of 2× 2 sparse camera array for a two depth-layers scene. The reconstruction filter used in the proposed method can derived by integrating all the process in our previously proposed method into an one-shot process.

show abstract

Section: Introductionsupporting

confidence: 58%

Section: B Image Formation Model In the Multi-layered Rendering And mentioning

confidence: 99%

Section: A Problem Formulationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Direct filtering method for image based rendering

Kubota

Aizawa

Chen

2005

IEEE International Conference on Image Processing 2005

Self Cite

View full text Add to dashboard Cite

show abstract

“…It is worth refering to the work of Kubota et al [24], [25], [26], [27], where the authors use a set of linear filters for photometric adjustment of observations from a multi-focus system to obtain a fully focused, virtually rendered view. They also explain how visual special effects can be created based on the depth related defocus [26].…”

mentioning

confidence: 99%

Defocus morphing in real aperture images

Chaudhuri

2005

J. Opt. Soc. Am. A

View full text Add to dashboard Cite

We introduce a new concept called defocus morphing in real aperture images in this paper. View morphing is an existing example of shape preserving image morphing based on the motion cue. We prove that images can also be morphed based on the depth related defocus cue. This illustrates that the morphing operation is not necessarily a geometric process alone; one can also perform a photometry based morphing wherein the shape information is implicitly buried in the image intensity field. A theoretical understanding of the defocus morphing process has been presented in this paper. Mathematically we show that, given two observations of a 3D scene for different camera parameter settings, we can obtain a virtual observation for any camera parameter setting through a simple nonlinear combination of these observations.

show abstract

Image-Based Rendering

Chang

Chen

2014

Academic Press Library in Signal Processing: Volume 4 - Image, Video Processing and Analysis, Hardware, Audio, Acoustic and Spe

View full text Add to dashboard Cite

Virtual view synthesis through linear processing without geometry

Cited by 3 publications

References 5 publications

Direct filtering method for image based rendering

Direct filtering method for image based rendering

Defocus morphing in real aperture images

Image-Based Rendering

Contact Info

Product

Resources

About