Dual Frequency Transformer for Efficient SDR-to-HDR Translation

doi:10.1007/s11633-023-1418-8

CORC > 自动化研究所 > 中国科学院自动化研究所 > 学术期刊 > International Journal of Automation and Computing

	Dual Frequency Transformer for Efficient SDR-to-HDR Translation
	Gang Xu; Qibin Hou; Ming-Ming Cheng
刊名	Machine Intelligence Research
	2024
卷号	21 期号:3 页码:538-548
关键词	Standard-dynamic-range to high-dynamic-range (SDR-to-HDR) translation, Transformer, dual frequency attention (DFA), frequency-aware feature decomposition, efficient model
ISSN号	2731-538X
DOI	10.1007/s11633-023-1418-8
英文摘要	The SDR-to-HDR translation technique can convert the abundant standard-dynamic-range (SDR) media resources to high-dynamic-range (HDR) ones, which can represent high-contrast scenes, providing more realistic visual experiences. While recent vision Transformers have achieved promising performance in many low-level vision tasks, there are few works attempting to leverage Transformers for SDR-to-HDR translation. In this paper, we are among the first to investigate the performance of Transformers for SDR-to-HDR translation. We find that directly using the self-attention mechanism may involve artifacts in the results due to the inappropriate way to model long-range dependencies between the low-frequency and high-frequency components. Taking this into account, we advance the self-attention mechanism and present a dual frequency attention (DFA), which leverages the self-attention mechanism to separately encode the low-frequency structural information and high-frequency detail information. Based on the proposed DFA, we further design a multi-scale feature fusion network, named dual frequency Transformer (DFT), for efficient SDR-to-HDR translation. Extensive experiments on the HDRTV1K dataset demonstrate that our DFT can achieve better quantitative and qualitative performance than the recent state-of-the-art methods. The code of our DFT is made publicly available at https://github.com/CS-GangXu/DFT.
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/56481]
专题	自动化研究所_学术期刊_International Journal of Automation and Computing
作者单位	Tianjin Media Computing Center, College of Computer Science, Nankai University, Tianjin 300000, China
推荐引用方式 GB/T 7714	Gang Xu,Qibin Hou,Ming-Ming Cheng. Dual Frequency Transformer for Efficient SDR-to-HDR Translation[J]. Machine Intelligence Research,2024,21(3):538-548.
APA	Gang Xu,Qibin Hou,&Ming-Ming Cheng.(2024).Dual Frequency Transformer for Efficient SDR-to-HDR Translation.Machine Intelligence Research,21(3),538-548.
MLA	Gang Xu,et al."Dual Frequency Transformer for Efficient SDR-to-HDR Translation".Machine Intelligence Research 21.3(2024):538-548.