RefocusGAN: Scene Refocusing Using a Single Image

Sakurikar, Parikshit; Mehta, Ishit; Balasubramanian, Vineeth N; Narayanan, P. J.

doi:10.1007/978-3-030-01225-0_31

Cited by 8 publications

(3 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…By following [12], they then designed an encoder-decoder architecture to extract the geometric information from light field images [13]. Some works [15,33] focus on providing light field datasets with ground truth depth or AiF images for further use.…”

Section: Light Fieldmentioning

confidence: 99%

Bridging Unsupervised and Supervised Depth from Focus via All-in-Focus Supervision

Wang¹,

Wang

Liu

et al. 2021

Preprint

View full text Add to dashboard Cite

Depth estimation is a long-lasting yet important task in computer vision. Most of the previous works try to estimate depth from input images and assume images are all-in-focus (AiF), which is less common in real-world applications. On the other hand, a few works take defocus blur into account and consider it as another cue for depth estimation. In this paper, we propose a method to estimate not only a depth map but an AiF image from a set of images with different focus positions (known as a focal stack). We design a shared architecture to exploit the relationship between depth and AiF estimation. As a result, the proposed method can be trained either supervisedly with ground truth depth, or unsupervisedly with AiF images as supervisory signals. We show in various experiments that our method outperforms the state-of-the-art methods both quantitatively and qualitatively, and also has higher efficiency in inference time.

show abstract

Section: Light Fieldmentioning

confidence: 99%

Bridging Unsupervised and Supervised Depth from Focus via All-in-Focus Supervision

Wang¹,

Wang

Liu

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…In a related parallel effort, we have used data-driven methods for post-capture focus control. In [39], we propose an adversarial learning framework trained on focal stacks created from light-fields to refocus the scene after it has been captured. The task of refocusing is decomposed into disjoint Fig.…”

Section: Related Workmentioning

confidence: 99%

Geometric Scene Refocusing

Sakurikar¹,

Narayanan²

2020

Preprint

Self Cite

View full text Add to dashboard Cite

An image captured with a wide-aperture camera exhibits a finite depth-of-field, with focused and defocused pixels. A compact and robust representation of focus and defocus helps analyze and manipulate such images. In this work, we study the fine characteristics of images with a shallow depth-of-field in the context of focal stacks. We present a composite measure for focus that is a combination of existing measures. We identify in-focus pixels, dual-focus pixels, pixels that exhibit bokeh and spatiallyvarying blur kernels between focal slices. We use these to build a novel representation that facilitates easy manipulation of focal stacks. We present a comprehensive algorithm for post-capture refocusing in a geometrically correct manner. Our approach can refocus the scene at high fidelity while preserving fine aspects of focus and defocus blur.

show abstract

“…The generator and discriminator are trained in a min–max manner to improve the image quality of synthetic images. GAN has been shown to deblur the microscopic images acquired by various optical modalities. − Different GAN models have been reported including RefocusGAN, Deep-Z, FCFNN, W-Net, and Deep-R, toward rapid and automatic focus by out-of-focus images transformation. However, how GAN techniques recover structural and color information from blurred out-of-focus images and if it enables accurate and large-area characterization of 2D semiconductors have not been studied.…”

Section: Introductionmentioning

confidence: 99%

Microscopic Image Deblurring by a Generative Adversarial Network for 2D Nanomaterials: Implications for Wafer-Scale Semiconductor Characterization

Dong

Zhang

et al. 2022

ACS Appl. Nano Mater.

View full text Add to dashboard Cite

Wafer-scale two-dimensional (2D) semiconductors with atomically thin layers are promising materials for fabricating optic and photonic devices. Bright-field microscopy is a widely utilized method for large-area characterization, layer number identification, and quality assessment of 2D semiconductors based on optical contrast. Out-of-focus microscopic images caused by instrumental focus drifts contained blurred and degraded structural and color information, hindering the reliability of automated layer number identification of 2D nanosheets. To achieve automated restoration and accurate characterization, deep-learning-based microscopic imagery deblurring (MID) was developed. Specifically, a generative adversarial network with an improved loss function was employed to recover both the structural and color information of out-of-focus low-quality images. 2D MoS2 grown by the chemical vapor deposition on a SiO2/Si substrate was characterized. Quantitative indexes including structural similarity (SSIM), peak signal-to-noise ratio, and CIE 1931 color space were studied to evaluate the performance of MID for deblurring of out-of-focus images, with a minimum value of SSIM over 90% of deblurred images. Further, a pre-trained U-Net model with an average accuracy over 80% was implemented to segment and predict the layer number distribution of 2D nanosheet categories (monolayer, bilayer, trilayer, multi-layer, and bulk). The developed automated microscopic image deblurring using MID and the layer number identification by the U-Net model allow for on-site, accurate, and large-area characterization of 2D semiconductors for analyzing local optical properties. This method may be implemented in wafer-scale industrial manufacturing and quality monitoring of 2D photonic devices.

show abstract

RefocusGAN: Scene Refocusing Using a Single Image

Cited by 8 publications

References 24 publications

Bridging Unsupervised and Supervised Depth from Focus via All-in-Focus Supervision

Bridging Unsupervised and Supervised Depth from Focus via All-in-Focus Supervision

Geometric Scene Refocusing

Microscopic Image Deblurring by a Generative Adversarial Network for 2D Nanomaterials: Implications for Wafer-Scale Semiconductor Characterization

Contact Info

Product

Resources

About