Cascaded Attention Guidance Network for Single Rainy Image Restoration

Restoring a rainy image with raindrops or rainstreaks of varying scales, directions, and densities is an extremely challenging task. Recent approaches attempt to leverage the rain distribution (e.g., location) as prior to generate satisfactory results. However, concatenation of a single distribution...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on image processing : a publication of the IEEE Signal Processing Society. - 1992. - PP(2020) vom: 23. Sept.
1. Verfasser: Wang, Guoqing (VerfasserIn)
Weitere Verfasser: Sun, Changming, Sowmya, Arcot
Format: Online-Aufsatz
Sprache:English
Veröffentlicht: 2020
Zugriff auf das übergeordnete Werk:IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
Schlagworte:Journal Article
LEADER 01000caa a22002652 4500
001 NLM315371153
003 DE-627
005 20240229142856.0
007 cr uuu---uuuuu
008 231225s2020 xx |||||o 00| ||eng c
024 7 |a 10.1109/TIP.2020.3023773  |2 doi 
028 5 2 |a pubmed24n1303.xml 
035 |a (DE-627)NLM315371153 
035 |a (NLM)32966217 
040 |a DE-627  |b ger  |c DE-627  |e rakwb 
041 |a eng 
100 1 |a Wang, Guoqing  |e verfasserin  |4 aut 
245 1 0 |a Cascaded Attention Guidance Network for Single Rainy Image Restoration 
264 1 |c 2020 
336 |a Text  |b txt  |2 rdacontent 
337 |a ƒaComputermedien  |b c  |2 rdamedia 
338 |a ƒa Online-Ressource  |b cr  |2 rdacarrier 
500 |a Date Revised 22.02.2024 
500 |a published: Print-Electronic 
500 |a Citation Status Publisher 
520 |a Restoring a rainy image with raindrops or rainstreaks of varying scales, directions, and densities is an extremely challenging task. Recent approaches attempt to leverage the rain distribution (e.g., location) as prior to generate satisfactory results. However, concatenation of a single distribution map with the rainy image or with intermediate feature maps is too simplistic to fully exploit the advantages of such priors. To further explore this valuable information, an advanced cascaded attention guidance network, dubbed as CAG-Net, is formulated and designed as a three-stage model. In the first stage, a multitask learning network is constructed for producing the attention map and coarse de-raining results simultaneously. Subsequently, the coarse results and the rain distribution map are concatenated and fed to the second stage for results refinement. In this stage, the attention map generation network from the first stage is used to formulate a novel semantic consistency loss for better detail recovery. In the third stage, a novel pyramidal "whereand- how" learning mechanism is formulated. At each pyramid level, a two-branch network is designed to take the features from previous stages as inputs to generate better attention-guidance features and de-raining features, which are then combined via a gating scheme to produce the final de-raining results. Moreover, the uncertainty maps are also generated in this stage for more accurate pixel-wise loss calculation. Extensive experiments are carried out for removing raindrops or rainstreaks from both synthetic and real rainy images, and CAG-Net is demonstrated to produce significantly better results than state-of-the-art models. Code will be publicly available after paper acceptance 
650 4 |a Journal Article 
700 1 |a Sun, Changming  |e verfasserin  |4 aut 
700 1 |a Sowmya, Arcot  |e verfasserin  |4 aut 
773 0 8 |i Enthalten in  |t IEEE transactions on image processing : a publication of the IEEE Signal Processing Society  |d 1992  |g PP(2020) vom: 23. Sept.  |w (DE-627)NLM09821456X  |x 1941-0042  |7 nnns 
773 1 8 |g volume:PP  |g year:2020  |g day:23  |g month:09 
856 4 0 |u http://dx.doi.org/10.1109/TIP.2020.3023773  |3 Volltext 
912 |a GBV_USEFLAG_A 
912 |a SYSFLAG_A 
912 |a GBV_NLM 
912 |a GBV_ILN_350 
951 |a AR 
952 |d PP  |j 2020  |b 23  |c 09