Presentation 2019-08-29
[Short Paper] Impression estimation of 3D shape considering the influence of gaze direction DNN using multi-viewpoint image group
Keisuke Sakashita, Kensuke Tobitani, Kouichi Taguchi, Iori Tani, Sho Hashimoto, Kenji Katahira, Manabu Hashimoto, Noriko Nagata,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) To estimate how a three-dimensional shape makes a person feel, a method using the deep neural network with multi-viewpoint images was proposed in previous research. In this study, we focused on the importance of each viewpoint for the purpose of improving the accuracy of previous research, and examined the relationship between the feature of the shape and the importance of the viewpoint using three shape categories. As a result, it was found that the bias of importance differs from viewpoint to viewpoint according to the degree of freedom of each category. Two results supporting the validity of previous studies were obtained. Reflecting these results in the network structure is expected to improve the accuracy of previous research.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) DNN / Impression estimation / Multi-viewpoint image / 3D shape / Kansei / semantic differential scale method
Paper # MVE2019-11
Date of Issue 2019-08-22 (MVE)

Conference Information
Committee MVE
Conference Date 2019/8/29(2days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair Kenji Mase(Nagoya Univ.)
Vice Chair Masayuki Ihara(NTT)
Secretary Masayuki Ihara(Nagoya Univ.)
Assistant Satoshi Nishiguchi(Oosaka Inst. of Tech.) / Masanori Yokoyama(NTT) / Shogo Fukushima(Univ. of ToKyo)

Paper Information
Registration To Technical Committee on Media Experience and Virtual Environment
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) [Short Paper] Impression estimation of 3D shape considering the influence of gaze direction DNN using multi-viewpoint image group
Sub Title (in English)
Keyword(1) DNN
Keyword(2) Impression estimation
Keyword(3) Multi-viewpoint image
Keyword(4) 3D shape
Keyword(5) Kansei
Keyword(6) semantic differential scale method
1st Author's Name Keisuke Sakashita
1st Author's Affiliation Kwansei Gakuin University(Kwansei Gakuin Univ.)
2nd Author's Name Kensuke Tobitani
2nd Author's Affiliation Kwansei Gakuin University(Kwansei Gakuin Univ.)
3rd Author's Name Kouichi Taguchi
3rd Author's Affiliation Chukyo University(Chukyo Univ.)
4th Author's Name Iori Tani
4th Author's Affiliation Kwansei Gakuin University(Kwansei Gakuin Univ.)
5th Author's Name Sho Hashimoto
5th Author's Affiliation Kwansei Gakuin University(Kwansei Gakuin Univ.)
6th Author's Name Kenji Katahira
6th Author's Affiliation Kwansei Gakuin University(Kwansei Gakuin Univ.)
7th Author's Name Manabu Hashimoto
7th Author's Affiliation Chukyo University(Chukyo Univ.)
8th Author's Name Noriko Nagata
8th Author's Affiliation Kwansei Gakuin University(Kwansei Gakuin Univ.)
Date 2019-08-29
Paper # MVE2019-11
Volume (vol) vol.119
Number (no) MVE-190
Page pp.pp.35-36(MVE),
#Pages 2
Date of Issue 2019-08-22 (MVE)