TY - GEN
T1 - EIFFHDR
T2 - 2024 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2024
AU - Zhang, Xiang
AU - Zhu, Qiang
AU - Hu, Tao
AU - Yan, Qingsen
N1 - Publisher Copyright:
© 2024 IEEE.
PY - 2024
Y1 - 2024
N2 - While recent progress in Multi-exposure HDR imaging is promising, the growing complexity of state-of-the-art (SOTA) methods poses challenges for their analysis and comparison. In this paper, we analyze the motivations and approaches behind previous SOTA works and introduce EiffHDR, an efficient Multi-exposure HDR imaging technique. In contrast to prior methods employing multiple branches spatial attention mechanisms, EiffHDR adopts a streamlined gating mechanism for information flow control at both spatial and channel levels, enabling implicit alignment. Subsequently, we process these features through proposed Efficient Merging Network, facilitating long-range correlations and multi-scale information perception, ultimately producing high-quality HDR images. Our experiments demonstrate that EiffHDR not only achieves outstanding performance but also significantly reduces computational complexity, making it a valuable contribution to the field.
AB - While recent progress in Multi-exposure HDR imaging is promising, the growing complexity of state-of-the-art (SOTA) methods poses challenges for their analysis and comparison. In this paper, we analyze the motivations and approaches behind previous SOTA works and introduce EiffHDR, an efficient Multi-exposure HDR imaging technique. In contrast to prior methods employing multiple branches spatial attention mechanisms, EiffHDR adopts a streamlined gating mechanism for information flow control at both spatial and channel levels, enabling implicit alignment. Subsequently, we process these features through proposed Efficient Merging Network, facilitating long-range correlations and multi-scale information perception, ultimately producing high-quality HDR images. Our experiments demonstrate that EiffHDR not only achieves outstanding performance but also significantly reduces computational complexity, making it a valuable contribution to the field.
KW - High dynamic range imaging
KW - convolutional neural network
KW - multi-exposed imaging
UR - http://www.scopus.com/inward/record.url?scp=85191284685&partnerID=8YFLogxK
U2 - 10.1109/ICASSP48485.2024.10446711
DO - 10.1109/ICASSP48485.2024.10446711
M3 - 会议稿件
AN - SCOPUS:85191284685
T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
SP - 6560
EP - 6564
BT - 2024 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2024 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 14 April 2024 through 19 April 2024
ER -