Multi-scale contextual attention based hdr reconstruction of dynamic scenes

Yipeng Deng, Qin Liu, Takeshi Ikenaga

研究成果: Conference contribution

1 被引用数 (Scopus)

抄録

High dynamic range (HDR) image reconstruction of dynamic scenes from several low dynamic range (LDR) images captured with different exposure time is a challenging problem. Although several methods based on optical flow or patch-match have been proposed to address this problem, they are not robust enough and results still suffer from ghost-like artifacts for challenging scenes where large foreground motions exist. To this end, this paper proposes a multi-scale contextual attention guided alignment network called CAHDRNet and presents some evaluation results. In stark contrast to methods based on optical flow, this paper demonstrates that HDR reconstruction can be formulated as an image inpainting task and CAHDRNet conducts patch replacement on the deep feature maps unlike previous patch-based reconstruction methods. The contextual attention module proposed by an image inpainting work is extended in CAHDRNet with multi-scale attention rebalance to help model flexibly handle different scenes and reduce patch replacement error. Experiments on the public dataset indicate that the proposed CAHDRNet produces ghost-free results where detail in ill-exposed areas is well recovered. The proposed method scores 40.97 on test sequences with PSNR metric averagely while the best PSNR score of non-flow-based methods is 38.60. The flow-based method scores 40.95 with PSNR metric while it has 5 points better score than our result with HDR-VDP-2 metric. According to quantitative and qualitative evaluations, the proposed method outperforms all non-flow-based methods and has its merits and demerits compared with the flow-based method.

本文言語English
ホスト出版物のタイトルTwelfth International Conference on Digital Image Processing, ICDIP 2020
編集者Xudong Jiang, Hiroshi Fujita
出版社SPIE
ISBN(電子版)9781510638457
DOI
出版ステータスPublished - 2020
イベント12th International Conference on Digital Image Processing, ICDIP 2020 - Osaka, Japan
継続期間: 2020 5 192020 5 22

出版物シリーズ

名前Proceedings of SPIE - The International Society for Optical Engineering
11519
ISSN(印刷版)0277-786X
ISSN(電子版)1996-756X

Conference

Conference12th International Conference on Digital Image Processing, ICDIP 2020
国/地域Japan
CityOsaka
Period20/5/1920/5/22

ASJC Scopus subject areas

  • 電子材料、光学材料、および磁性材料
  • 凝縮系物理学
  • コンピュータ サイエンスの応用
  • 応用数学
  • 電子工学および電気工学

フィンガープリント

「Multi-scale contextual attention based hdr reconstruction of dynamic scenes」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