Presentation 2019-12-19
Scene-Independent Optimum View Interpolation Filters for Stereo Images
Akira Kubota, Seiji Nakatsubo,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this paper, we theoretically derive view-interpolation filters that reconstruct intermediate view images from stereo images without depth estimation. Assuming that scene is composed of multiple layer images, we model the stereo images and the intermediate images as a sum of shifted layer imagesand derive the filters in a least squared fashion. Simulation results showed that the intermediate images can be reconstructed with adequate quality (over 30 dB in PSNR) through the presented filters for the case of smaller disparity (baseline distance).
Keyword(in Japanese) (See Japanese page)
Keyword(in English) stereo images / pseudo-inverse matrix / view interpolation / space-invariant filters
Paper # PRMU2019-48
Date of Issue 2019-12-12 (PRMU)

Conference Information
Committee PRMU
Conference Date 2019/12/19(2days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair Yoichi Sato(Univ. of Tokyo)
Vice Chair Toru Tamaki(Hiroshima Univ.) / Akisato Kimura(NTT)
Secretary Toru Tamaki(NTT) / Akisato Kimura(OMRON SINICX)
Assistant Yusuke Uchida(DeNA) / Takayoshi Yamashita(Chubu Univ.)

Paper Information
Registration To Technical Committee on Pattern Recognition and Media Understanding
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Scene-Independent Optimum View Interpolation Filters for Stereo Images
Sub Title (in English)
Keyword(1) stereo images
Keyword(2) pseudo-inverse matrix
Keyword(3) view interpolation
Keyword(4) space-invariant filters
1st Author's Name Akira Kubota
1st Author's Affiliation Chuo University(Chuo Univ.)
2nd Author's Name Seiji Nakatsubo
2nd Author's Affiliation Chuo University(Chuo Univ.)
Date 2019-12-19
Paper # PRMU2019-48
Volume (vol) vol.119
Number (no) PRMU-347
Page pp.pp.13-16(PRMU),
#Pages 4
Date of Issue 2019-12-12 (PRMU)