Revisiting Depth Image Fusion with Variational Message Passing

Diego Thomas, Ekaterina Sirazitdinova, Akihiro Sugimoto, Rin Ichsiro Taniguchi

研究成果: Chapter in Book/Report/Conference proceedingConference contribution

抄録

The running average approach has long been perceived as the best choice for fusing depth measurements captured by a consumer-grade RGB-D camera into a global 3D model. This strategy, however, assumes exact correspondences between points in a 3D model and points in the captured RGB-D images. Such assumption does not hold true in many cases because of errors in motion tracking, noise, occlusions, or inconsistent surface sampling during measurements. Accordingly, reconstructed 3D models suffer unpleasant visual artifacts. In this paper, we visit the depth fusion problem from a probabilistic viewpoint and formulate it as a probabilistic optimization using variational message passing in a Bayesian network. Our formulation enables us to fuse depth images robustly, accurately, and fast for high quality RGB-D keyframe creation, even if exact point correspondences are not always available. Our formulation also allows us to smoothly combine depth and color information for further improvements without increasing computational speed. The quantitative and qualitative comparative evaluation on built keyframes of indoor scenes show that our proposed framework achieves promising results for reconstructing accurate 3D models while using low computational power and being robust against misalignment errors without post-processing.

本文言語英語
ホスト出版物のタイトルProceedings - 2019 International Conference on 3D Vision, 3DV 2019
出版社Institute of Electrical and Electronics Engineers Inc.
ページ328-337
ページ数10
ISBN(電子版)9781728131313
DOI
出版ステータス出版済み - 9 2019
イベント7th International Conference on 3D Vision, 3DV 2019 - Quebec, カナダ
継続期間: 9 15 20199 18 2019

出版物シリーズ

名前Proceedings - 2019 International Conference on 3D Vision, 3DV 2019

会議

会議7th International Conference on 3D Vision, 3DV 2019
国/地域カナダ
CityQuebec
Period9/15/199/18/19

All Science Journal Classification (ASJC) codes

  • コンピュータ ビジョンおよびパターン認識
  • メディア記述
  • モデリングとシミュレーション

フィンガープリント

「Revisiting Depth Image Fusion with Variational Message Passing」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