Accuracy Improvement of Depth Map Estimation from Multi-View Images Using NeRF

Shintaro Ito, Kanta Miura, Koichi Ito, Takafumi Aoki

研究成果: 書籍の章/レポート/Proceedings会議への寄与査読

抄録

In this paper, we propose a method to improve the accuracy of depth map estimation from multi-view images using Neural Radiance Fields (NeRF). A depth map can be estimated from multi-view images using Multi-View Stereo (MVS), which can estimates the depths inside objects with high accuracy, while NeRF can estimate the depths at object boundaries with high accuracy. We consider using both advantages to improve the accuracy of depth map estimation from multi-view images and making NeRF as a refinement module. Through a set of experiments using a public MVS dataset, we demonstrate the effectiveness of the proposed method compared to conventional depth map estimation methods.

本文言語英語
ホスト出版物のタイトル2023 IEEE International Conference on Visual Communications and Image Processing, VCIP 2023
出版社Institute of Electrical and Electronics Engineers Inc.
ISBN(電子版)9798350359855
DOI
出版ステータス出版済み - 2023
イベント2023 IEEE International Conference on Visual Communications and Image Processing, VCIP 2023 - Jeju, 大韓民国
継続期間: 2023 12月 42023 12月 7

出版物シリーズ

名前2023 IEEE International Conference on Visual Communications and Image Processing, VCIP 2023

会議

会議2023 IEEE International Conference on Visual Communications and Image Processing, VCIP 2023
国/地域大韓民国
CityJeju
Period23/12/423/12/7

フィンガープリント

「Accuracy Improvement of Depth Map Estimation from Multi-View Images Using NeRF」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル