Presentation 2023-05-19
Learning static NeRF representations from video using 2D segmentation masks
Takashi Otonari, Satoshi Ikehata, Kiyoharu Aizawa,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this paper, we tackle the problem of extracting static backgrounds from videos containing moving objects, such as people and cars. RobustNeRF, the current state-of-the-art method for extracting static backgrounds, often struggles to separate high-frequency static backgrounds from dynamic foregrounds in real-world scenes. We introduce Test Time Augmentation, and our experiments demonstrate that the additional segmentation masks effectively remove dynamic foregrounds in scenes with high-frequency static backgrounds, an area where existing methods have faced difficulties.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) neural radiance field / NeRF / novel view synthesis / scene decomposition / semantic segmentation
Paper # PRMU2023-7
Date of Issue 2023-05-11 (PRMU)

Conference Information
Committee PRMU / IPSJ-CVIM
Conference Date 2023/5/18(2days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair Seiichi Uchida(Kyushu Univ.)
Vice Chair Takuya Funatomi(NAIST) / Mitsuru Anpai(Denso IT Lab.)
Secretary Takuya Funatomi(CyberAgent) / Mitsuru Anpai(Univ. of Tokyo)
Assistant Nakamasa Inoue(Tokyo Inst. of Tech.) / Yasutomo Kawanishi(Riken)

Paper Information
Registration To Technical Committee on Pattern Recognition and Media Understanding / Special Interest Group on Computer Vision and Image Media
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Learning static NeRF representations from video using 2D segmentation masks
Sub Title (in English)
Keyword(1) neural radiance field
Keyword(2) NeRF
Keyword(3) novel view synthesis
Keyword(4) scene decomposition
Keyword(5) semantic segmentation
1st Author's Name Takashi Otonari
1st Author's Affiliation The University of Tokyo(Tokyo Univ.)
2nd Author's Name Satoshi Ikehata
2nd Author's Affiliation National Institute of Informatics(NII)
3rd Author's Name Kiyoharu Aizawa
3rd Author's Affiliation The University of Tokyo(Tokyo Univ.)
Date 2023-05-19
Paper # PRMU2023-7
Volume (vol) vol.123
Number (no) PRMU-30
Page pp.pp.33-38(PRMU),
#Pages 6
Date of Issue 2023-05-11 (PRMU)