| アイテムタイプ |
共通アイテムタイプ(1) |
| 公開日 |
2025-01-16 |
| タイトル |
|
|
タイトル |
ManifoldNeRF: View-dependent Image Feature Supervision for Few-shot Neural Radiance Fields |
|
言語 |
en |
| 著者 |
Kanaoka, Daiju
Sonogashira, Motoharu
田向, 権
Kawanishi, Yasutomo
|
| 著作権関連情報 |
|
|
権利情報 |
Copyright (c) 2023. The copyright of this document resides with its authors. It may be distributed unchanged freely in print or electronic forms. |
| 抄録 |
|
|
内容記述タイプ |
Abstract |
|
内容記述 |
Novel view synthesis has recently made significant progress with the advent of Neural Radiance Fields (NeRF). DietNeRF is an extension of NeRF that aims to achieve this task from only a few images by introducing a new loss function for unknown viewpoints with no input images. The loss function assumes that a pre-trained feature extractor should output the same feature even if input images are captured at different viewpoints since the images contain the same object. However, while that assumption is ideal, in reality, it is known that as viewpoints continuously change, also feature vectors continuously change. Thus, the assumption can harm training. To avoid this harmful training, we propose ManifoldNeRF, a method for supervising feature vectors at unknown viewpoints using interpolated features from neighboring known viewpoints. Since the method provides appropriate supervision for each unknown viewpoint by the interpolated features, the volume representation is learned better than DietNeRF. Experimental results show that the proposed method performs better than others in a complex scene. We also experimented with several subsets of viewpoints from a set of viewpoints and identified an effective set of viewpoints for real environments. This provided a basic policy of viewpoint patterns for real-world application. The code is available at https://github.com/haganelego/ManifoldNeRF_BMVC2023 |
|
言語 |
en |
| 備考 |
|
|
内容記述タイプ |
Other |
|
内容記述 |
The 34th British Machine Vision Conference, BMVC2023, 20 - 24 November 2023, Aberdeen, UK |
| 書誌情報 |
発行日 2023-11-21
|
| 言語 |
|
|
言語 |
eng |
| 資源タイプ |
|
|
資源タイプ識別子 |
http://purl.org/coar/resource_type/c_5794 |
|
資源タイプ |
conference paper |
| 出版タイプ |
|
|
出版タイプ |
VoR |
|
出版タイプResource |
http://purl.org/coar/version/c_970fb48d4fbd8a85 |
| 会議記述 |
|
|
|
会議名 |
British Machine Vision Conference |
|
回次 |
34 |
|
|
開始年 |
2023 |
|
|
開始月 |
11 |
|
|
開始日 |
10 |
|
|
終了年 |
2023 |
|
|
終了月 |
11 |
|
|
終了日 |
24 |
|
開催国 |
GBR |
| 査読の有無 |
|
|
値 |
yes |
| 研究者情報 |
|
|
URL |
https://hyokadb02.jimu.kyutech.ac.jp/html/100000641_ja.html |
| 論文ID（連携） |
|
|
値 |
10444356 |
| 連携ID |
|
|
値 |
12910 |
10444356.pdf (11.9 MB)
