Related papers: Autoencoder-based holographic image restoration
Mask-based lensless imagers are smaller and lighter than traditional lensed cameras. In these imagers, the sensor does not directly record an image of the scene; rather, a computational algorithm reconstructs it. Typically, mask-based…
Image inpainting is a challenging problem as it needs to fill the information of the corrupted regions. Most of the existing inpainting algorithms assume that the positions of the corrupted regions are known. Different from the existing…
Machine learning and many of its applications are considered hard to approach due to their complexity and lack of transparency. One mission of human-centric machine learning is to improve algorithm transparency and user satisfaction while…
Color encoding of depth is shown to occur naturally in holograms that are reconstructed under white light illumination. It can be registered in a common color photograph, allowing a simple method of visual decoding by means of ordinary…
Coherent diffractive imaging is a technique that recovers the sample image by numerically inverting its diffraction pattern. We propose a generalization of this method for the inversion of multi-wavelength data. Using this approach, we show…
We present a `CLAssifier-DECoder' architecture (\emph{ClaDec}) which facilitates the comprehension of the output of an arbitrary layer in a neural network (NN). It uses a decoder to transform the non-interpretable representation of the…
Bottleneck autoencoders have been actively researched as a solution to image compression tasks. However, we observed that bottleneck autoencoders produce subjectively low quality reconstructed images. In this work, we explore the ability of…
Over the past years, the ever-growing trend on data storage demand, more specifically for "cold" data (rarely accessed data), has motivated research for alternative systems of data storage. Because of its biochemical characteristics,…
Deep learning techniques have revolutionized the fields of image restoration and image quality assessment in recent years. While image restoration methods typically utilize synthetically distorted training data for training, deep quality…
Autoencoders learn data representations (codes) in such a way that the input is reproduced at the output of the network. However, it is not always clear what kind of properties of the input data need to be captured by the codes. Kernel…
Digital holography numerically restores three-dimensional image information using optically captured diffractive waves. The required bandwidth is larger than that of hologram pixel at a closer distance in the Fresnel diffraction regime,…
Image restoration is a long-standing low-level vision problem, e.g., deblurring and deraining. In the process of image restoration, it is necessary to consider not only the spatial details and contextual information of restoration to ensure…
This paper investigates a novel algorithmic approach to data representation based on kernel methods. Assuming that the observations lie in a Hilbert space X, the introduced Kernel Autoencoder (KAE) is the composition of mappings from…
This work presents the optical reconstruction of computer-generated holograms (CGHs) 3D scenes via spatial light modulators (SLMs). Holography is an optical technique that allows the recording and reconstruction of images of 3D objects, as…
Memory-effect-based methods have been demonstrated to be feasible to observe hidden objects through thin scattering layers, even from a single-shot speckle pattern. However, most of the existing methods are performed with narrowband…
The shutter strategy applied to the photo-shooting process has a significant influence on the quality of the captured photograph. An improper shutter may lead to a blurry image, video discontinuity, or rolling shutter artifact. Existing…
This paper addresses the problem of inverse rendering from photometric images. Existing approaches for this problem suffer from the effects of self-shadows, inter-reflections, and lack of constraints on the surface reflectance, leading to…
The low dynamic range (LDR) of common cameras fails to capture the rich contrast in natural scenes, resulting in loss of color and details in saturated pixels. Reconstructing the high dynamic range (HDR) of luminance present in the scene…
This paper proposes a visual encryption method to ensure the confidentiality of digital images. The model used is based on an autoencoder using aConvolutional Neural Network (CNN) to ensure the protection of the user data on both the sender…
Conventionally, autoencoders are unsupervised representation learning tools. In this work, we propose a novel discriminative autoencoder. Use of supervised discriminative learning ensures that the learned representation is robust to…