Image Demoireing with Learnable Bandpass Filters

Zheng, Bolun; Yuan, Shanxin; Slabaugh, Greg; Leonardis, Aleš

doi:10.1109/cvpr42600.2020.00369

Cited by 65 publications

(69 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To verify the effectiveness of the proposed method, extensive qualitative and quantitative experiments are performed on the real‐world ISAR images. Seven state‐of‐the‐art approaches are selected as reference: Expected Patch Log Likelihood (EPLL), 27 Non‐Local Means (NL‐Means), 28 Block‐Matching and 3D Filtering (BM3D), 29 Non‐Local Bayes (NL Bayes), 30 Bayes Least Squares‐Gaussian Scale Mixtures (BLS‐GSM), 31 Discrete Cosine Transform (DCT) 25 and Multiscale DCT (MSDCT) 32 …”

Section: Resultsmentioning

confidence: 99%

Dynamic coarse‐to‐fine ISAR image blind denoising using active joint prior learning

Xue

Feng

et al. 2021

Int J Intell Syst

View full text Add to dashboard Cite

Most existing nonblind denoising approaches assumed the noise to be homogeneous white Gaussian distribution with known intensity. However, it is difficult to know beforehand or model accurately real‐world noises with complex hybrid distribution and noise intensity. In this paper, active joint prior learning (JPL) is proposed for real‐world ISAR image blind denoising. (1) To explore strong model hierarchy and components relationship automatically, a novel graphical Dirichlet mixture process (GDMP) model is developed, where the latent representations and component hyperparameters are jointly learned from each other. (2) A multiscale joint learning strategy (MJLS) is proposed to take advantage of both the optimization‐ and discriminative learning‐based capabilities. The external noiseless, internal noisy image information and their relationships are jointly explored simultaneously. (3) Low‐rank weighted sparse learning (LWSL) is proposed to learn sparse discriminative correlation components for robust prior learning, and latent low‐rank embedding for GDMP patterns self‐adaptive inference. Extensive experimental results on ISAR image datasets demonstrate the effectiveness of the proposed model for both synthesis and real‐world noisy ISAR images, and the proposed method outperforms the state‐of‐the‐art denoising methods.

show abstract

Section: Resultsmentioning

confidence: 99%

Dynamic coarse‐to‐fine ISAR image blind denoising using active joint prior learning

Xue

Feng

et al. 2021

Int J Intell Syst

View full text Add to dashboard Cite

show abstract

“…5. Visual comparison of demoiréing results among state-of-the-art approaches including DMCNN [1], MBCNN [5] and our method on the samples in LCDMoiré dataset. ment of 1.53dB in PSNR.…”

Section: Ablation Studymentioning

confidence: 99%

“…* corresponding authors. Recent methods [1][2] [3][4] [5] treat image demoiréing as an image restoration problem addressed by CNN-based models. For instance, Sun et al [1] proposed a multi-resolution convolutional neural network, according to the fact that the moiré pattern spans over a wide range of frequency bands, to accomplish the task with a large-scale dataset for demoiréing released.…”

Section: Introductionmentioning

confidence: 99%

“…For instance, Sun et al [1] proposed a multi-resolution convolutional neural network, according to the fact that the moiré pattern spans over a wide range of frequency bands, to accomplish the task with a large-scale dataset for demoiréing released. Its follow-ups, with methods [2] [5] as representatives, also applied multi-scale based structures to do the job. Besides, Zheng et al [5] and Liu et al [4] adopted the frequency prior, which could distinguish moiré patterns from natural image patterns better.…”

Section: Introductionmentioning

confidence: 99%

“…Its follow-ups, with methods [2] [5] as representatives, also applied multi-scale based structures to do the job. Besides, Zheng et al [5] and Liu et al [4] adopted the frequency prior, which could distinguish moiré patterns from natural image patterns better. He et al [3] introduced additional labeled data in [1] based on shape, colour, and frequency characteristics for precise moiré pattern removal.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Image Demoiréing with a Dual-Domain Distilling Network

Wang

Guo

2021

2021 IEEE International Conference on Multimedia and Expo (ICME)

View full text Add to dashboard Cite

Due to slight discrepancy of spatial frequency between the camera sensor array and sub-pixel layout of LCD monitor, moiré pattern artifacts appear in various shapes and colours which seriously degrade the quality of captured images. It is challenging yet practically crucial to remove moiré artifacts from a single camera-captured screen image. In this paper, we propose a dual-domain distilling network (3DNet for short) to tackle this problem in an end-to-end manner. The 3DNet consists of a dual-branch student network (a.k.a. demoiréing network), and two teacher networks. The two branches of student network exploit knowledge in both spatial-domain and frequency-domain for the sake of removing moiré artifacts, based on the observation that rich image details can be discovered in the frequency-domain while structure information can be well kept in the spatial-domain. The demoiréing process of two branches is supervised by the knowledge distilled from two teacher networks trained for reconstructing clear images in the spatial and frequency domains respectively. Comprehensive experimental results are conducted to demonstrate the efficacy of our design, and reveal its superiority over state-ofthe-art alternatives.

show abstract