https://scholars.lib.ntu.edu.tw/handle/123456789/607101
標題: | Speed Up Light Field Synthesis from Stereo Images | 作者: | Chen Y.-C Chao C.-H Liu C.-L Shih K.-T HOMER H. CHEN |
關鍵字: | CNN;Deep learning;Light field reconstruction;Light field synthesis;Stereo vision;Image reconstruction;Pipelines;Stereo image processing;Disparity estimations;Field synthesis;Light fields;Neural-networks;Speed up;Stereoimages | 公開日期: | 2021 | 起(迄)頁: | 47-53 | 來源出版物: | Proceedings - 2021 4th IEEE International Conference on Artificial Intelligence and Virtual Reality, AIVR 2021 | 摘要: | In this paper, we focus on the speedup of a learning-based light field synthesis pipeline. The pipeline involves a disparity estimation neural network and a light field blending component. The former achieves high speed performance through the use of feature extraction and multi-stage disparity refinement, while the latter warps and merges coarse light fields generated from the left and right disparity maps in a novel and efficient way. The pipeline can produce a full light field in less than 1/10 of a second, while retaining fairly reasonable image quality. The model itself has a very low parameter count, which is ideal for devices with limited computational power. ? 2021 IEEE |
URI: | https://www.scopus.com/inward/record.uri?eid=2-s2.0-85124238418&doi=10.1109%2fAIVR52153.2021.00016&partnerID=40&md5=c962587d6d282fbbdefc62361c08094c https://scholars.lib.ntu.edu.tw/handle/123456789/607101 |
DOI: | 10.1109/AIVR52153.2021.00016 |
顯示於: | 電機工程學系 |
在 IR 系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。