Virtual view rendering using super-resolution with multiview images

Authors:
Bumsub Ham;Dongbo Min;Jinwook Choi;Kwanghoon Sohn
Affiliations:
Dept. of Electrical and Electronic Eng., Yonsei University, Seoul, Korea;Dept. of Electrical and Electronic Eng., Yonsei University, Seoul, Korea;Dept. of Electrical and Electronic Eng., Yonsei University, Seoul, Korea;Dept. of Electrical and Electronic Eng., Yonsei University, Seoul, Korea
Venue:
ICIP'09 Proceedings of the 16th IEEE international conference on Image processing
Year:
2009

Citing 9
Cited 0

Feature-oriented image enhancement using shock filters

SIAM Journal on Numerical Analysis
View interpolation for image synthesis

SIGGRAPH '93 Proceedings of the 20th annual conference on Computer graphics and interactive techniques
Physically-Valid View Synthesis by Image Interplation

VSR '95 Proceedings of the IEEE Workshop on Representation of Visual Scenes
Real-time backward disparity-based rendering for dynamic scenes using programmable graphics hardware

GI '07 Proceedings of Graphics Interface 2007
Super-resolution for synthetic zooming

EURASIP Journal on Applied Signal Processing
Super-Resolution Stereo- and Multi-View Synthesis from Monocular Video Sequences

3DIM '07 Proceedings of the Sixth International Conference on 3-D Digital Imaging and Modeling
View generation with 3D warping using depth information for FTV

Image Communication
A fast super-resolution reconstruction algorithm for pure translational motion and common space-invariant blur

IEEE Transactions on Image Processing
Reconstructing Dense Light Field From Array of Multifocus Images for Novel View Synthesis

IEEE Transactions on Image Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents a new approach to solve the problem of quality degradation of a synthesized view, when a virtual camera moves forward. Interpolation techniques using only two neighboring views are generally applied when a virtual view is synthesized. Because the size of an object increases when the virtual camera moves forward, conventional methods have usually addressed this problem by interpolation techniques in order to synthesize a virtual view. However, as it generates a degraded view such as blurred images, we prevent a synthesized view from being blurred by using more images in multiview camera configuration. That is, this problem is solved by applying super-resolution concept which reconstructs a high resolution image from several low resolution images. Data fusion is performed by geometric warping with disparity maps of the multiple images followed by deblurring. Experimental results show that the image quality can further be improved by reducing blurring and halo effects in comparison with the interpolation method.