Deformable Aligned Fusion for Video Super Resolution

Sin Hong Lee, Chih Hung Kuo, Tsai Chun Yu

研究成果: Conference contribution

摘要

The key to the video super-resolution algorithm is to capture the information of adjacent frames to supplement the reconstruction of the current frame. It is necessary to apply the alignment operation to compensate the displacements of objects in different frames. We propose an innovative deformable aligned fusion block (DAFB) to exploit the complementary information from adjacent frames more efficiently. We also model the offsets of deformable alignments as probabilistic distributions to augment the robustness of a DAFB. Our proposed model outperforms state-of-the-art CNN-based models on benchmark testing datasets, including Vid4 and UDM10.

原文English
主出版物標題2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2023
發行者Institute of Electrical and Electronics Engineers Inc.
頁面357-364
頁數8
ISBN(電子)9798350300673
DOIs
出版狀態Published - 2023
事件2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2023 - Taipei, Taiwan
持續時間: 2023 10月 312023 11月 3

出版系列

名字2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2023

Conference

Conference2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2023
國家/地區Taiwan
城市Taipei
期間23-10-3123-11-03

All Science Journal Classification (ASJC) codes

  • 硬體和架構
  • 訊號處理
  • 人工智慧
  • 電腦科學應用

指紋

深入研究「Deformable Aligned Fusion for Video Super Resolution」主題。共同形成了獨特的指紋。

引用此