Contrastive Feature Decomposition for Image Reflection Removal

Feng, Xin; Ji, Haobo; Jiang, Bo; Pei, Wenjie; Chen, Fanglin; Lu, Guangming

doi:10.1109/icme51207.2021.9428089

Cited by 8 publications

(3 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“… In P17 [84], the proposed network first separates the extracted features into two branches using feature learning: background constituent and reflection constituent. The contrastive feature decomposition sub-network achieves more accurate feature decomposition by their proposed contrastive supervision algorithm.…”

Section: Rq4 What Are the Architectures Of The Proposed Reflection Re...mentioning

confidence: 99%

“…The contrastive feature decomposition sub-network achieves more accurate feature decomposition by their proposed contrastive supervision algorithm. In the end, the dense feature refinement sub-network tries to refine the details of restored images in order to accomplish images with high standard including both the background and the reflection images [84].…”

Section: Rq4 What Are the Architectures Of The Proposed Reflection Re...mentioning

confidence: 99%

See 1 more Smart Citation

Single-Image Reflection Removal Using Deep Learning: A Systematic Review

et al. 2022

View full text Add to dashboard Cite

Images captured through the glass often consist of undesirable specular reflections. These reflections detected in front of the glass remarkably reduce the quality and visibility of the scenes behind it. The process of reflection removal from images through the glass has many important applications in computer vision projects. Recently deep learning-based methods are being utilized for reflection removal so widely. In this article, we proposed a systematic literature review on the topic of single-image reflection removal using deep learning methods which were published between the years 2015 to 2021. A total number of 1600 research papers were extracted from five different online databases and digital libraries (IEEE Xplore, Google Scholar, Science Direct, SpringerLink and ACM Digital Library). After following the study selection procedure, 25 research papers were selected for this systematic review. The selected research papers were then analyzed to answer 7 key research questions that we have come up with to comprehensively explore the use of deep learning and neural networks for single-image reflection removal. After reading this article, future researchers will have a solid idea in the research field and will be able to work on their own research. The results provided in this proposed systematic review illustrate the main challenges that are encountered by researchers in this field and recommend encouraging directions for future research work. This review will also be helpful for researchers in discovering accessible datasets that can be used as benchmarks for comparing their proposed deep learning techniques with other studies in this research area.

show abstract

Section: Rq4 What Are the Architectures Of The Proposed Reflection Re...mentioning

confidence: 99%

Section: Rq4 What Are the Architectures Of The Proposed Reflection Re...mentioning

confidence: 99%

Single-Image Reflection Removal Using Deep Learning: A Systematic Review

et al. 2022

View full text Add to dashboard Cite

show abstract

“…We perform human evaluation to compare our model with other topthree most powerful methods for reflection removal including ERRNet [2], IBCLN [1] and DMGN [8]. We randomly select We conduct experiments to compare our GLSGN with nine state-of-theart methods [1], [2], [7]- [9], [30], [41], [48], [49] for image reflection removal on five datasets including our proposed ultra high-resolution datasets as UHR4K-Real and UHR4K-Syn, and multiple public benchmark datasets with regular resolution as Real20 [40], Nature [1], and SIR 2 [37]. Table VII lists the quantitative results of various methods for image reflection removal on five datasets in terms of PSNR and SSIM.…”

Section: B Ablation Studymentioning

confidence: 99%

Global-Local Stepwise Generative Network for Ultra High-Resolution Image Restoration

Feng¹,

Ji²,

Pei³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

While the research on image background restoration from regular size of degraded images has achieved remarkable progress, restoring ultra high-resolution (e.g., 4K) images remains an extremely challenging task due to the explosion of computational complexity and memory usage, as well as the deficiency of annotated data. In this paper we present a novel model for ultra high-resolution image restoration, referred to as the Global-Local Stepwise Generative Network (GLSGN), which employs a stepwise restoring strategy involving four restoring pathways: three local pathways and one global pathway. The local pathways focus on conducting image restoration in a finegrained manner over local but high-resolution image patches, while the global pathway performs image restoration coarsely on the scale-down but intact image to provide cues for the local pathways in a global view including semantics and noise patterns. To smooth the mutual collaboration between these four pathways, our GLSGN is designed to ensure the interpathway consistency in four aspects in terms of low-level content, perceptual attention, restoring intensity and high-level semantics, respectively. As another major contribution of this work, we also introduce the first ultra high-resolution dataset to date for both reflection removal and rain streak removal, comprising 4,670 real-world and synthetic images. Extensive experiments across three typical tasks for image background restoration, including image reflection removal, image rain streak removal and image dehazing, show that our GLSGN consistently outperforms stateof-the-art methods.

show abstract

RETRACTED ARTICLE: Effective reflection removal system for cognitive based convolutional neural networks

Saptalakar

Latte

2022

Soft Comput

View full text Add to dashboard Cite

Contrastive Feature Decomposition for Image Reflection Removal

Cited by 8 publications

References 17 publications

Single-Image Reflection Removal Using Deep Learning: A Systematic Review

Single-Image Reflection Removal Using Deep Learning: A Systematic Review

Global-Local Stepwise Generative Network for Ultra High-Resolution Image Restoration

RETRACTED ARTICLE: Effective reflection removal system for cognitive based convolutional neural networks

Contact Info

Product

Resources

About