AI-based Holl-filling with Temporal Consistency

Li Jyun Chen, Jar Ferr Yang, Li Hong

研究成果: Conference contribution

摘要

Depth image-based rendering (DIBR) has been recently considered as a significant technology for generating 3D virtual views. However, the hole-filling method is still the main challenge in the DIBR engine because of the occlusions of foreground objects. While looking into the video sequences, the occluded parts in a frame may be revealed in the past or future frames. The temporal information could be the useful cues to recover the occlusions of the current frame. In this paper, we design an encoder-decoder neural model with a bounded region attention module to effectively fill the holes. This attention module is aim to extract the useful hints from neighbor frames.

原文English
主出版物標題ISPACS 2021 - International Symposium on Intelligent Signal Processing and Communication Systems
主出版物子標題5G Dream to Reality, Proceeding
發行者Institute of Electrical and Electronics Engineers Inc.
ISBN(電子)9781665419512
DOIs
出版狀態Published - 2021
事件2021 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2021 - Hualien, Taiwan
持續時間: 2021 11月 162021 11月 19

出版系列

名字ISPACS 2021 - International Symposium on Intelligent Signal Processing and Communication Systems: 5G Dream to Reality, Proceeding

Conference

Conference2021 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2021
國家/地區Taiwan
城市Hualien
期間21-11-1621-11-19

All Science Journal Classification (ASJC) codes

  • 人工智慧
  • 電腦網路與通信
  • 訊號處理
  • 安全、風險、可靠性和品質

指紋

深入研究「AI-based Holl-filling with Temporal Consistency」主題。共同形成了獨特的指紋。

引用此