Related papers: Reconfigurable structural color generation in mult…
We introduce the concept of `hyperpixels' in which each element of a pixel filter array (suitable for CMOS image sensor integration) has a spectral transmission tailored to a target spectral component expected in application-specific…
We introduce a novel technique for designing color filter metasurfaces using a data-driven approach based on deep learning. Our innovative approach employs inverse design principles to identify highly efficient designs that outperform all…
A multi-layer image is more valuable than a single-layer image from a graphic designer's perspective. However, most of the proposed image generation methods so far focus on single-layer images. In this paper, we propose MontageGAN, which is…
Modelling the impact of a material's mesostructure on device level performance typically requires access to 3D image data containing all the relevant information to define the geometry of the simulation domain. This image data must include…
In this work, a long-cavity semiconductor laser subject to optical feedback is exploited to generate repetitive temporal patterns with enhanced intra-pattern sample diversity. Stable limit cycle dynamics characterized by multiple frequency…
Nanostructured metasurfaces offer unique capabilities for local control of the phase and amplitude of transmitted and reflected optical waves. Based on this potential, a large number of metasurfaces have been proposed in recent years as…
Generative image models can produce convincingly real images, with plausible shapes, textures, layouts and lighting. However, one domain in which they perform notably poorly is in the synthesis of transparent objects, which exhibit…
Control over the physical properties of materials is ubiquitously required in many fields. One means by which this can be achieved is controlling the internal structure of multi-component materials with an eye to enhancing mechanical…
Phase retrieval is a nonlinear inverse problem that arises in a wide range of imaging modalities, from electron microscopy to Fourier ptychography. In particular, the reconstruction is facilitated when the sensing matrix is i.i.d. random,…
Transparent image layer generation plays a significant role in digital art and design workflows. Existing methods typically decompose transparent layers from a single RGB image using a set of tools or generate multiple transparent layers…
Image inpainting techniques have shown significant improvements by using deep neural networks recently. However, most of them may either fail to reconstruct reasonable structures or restore fine-grained textures. In order to solve this…
Exploring and editing colors in images is a common task in graphic design and photography. However, allowing for interactive recoloring while preserving smooth color blends in the image remains a challenging problem. We present…
A novel metasurface unit cell architecture is proposed to enable independent control of the reflection magnitude and phase at a desired operation frequency, while maintaining linear polarization of the incoming fields. The proposed…
This paper presents a novel and efficient image enhancement method based on pigment representation. Unlike conventional methods where the color transformation is restricted to pre-defined color spaces like RGB, our method dynamically adapts…
Graphic design images consist of multiple editable layers, such as text, background, and decorative elements, while most generative models produce rasterized outputs without explicit layer structures, limiting downstream editing. Existing…
When images are statistically described by a generative model we can use this information to develop optimum techniques for various image restoration problems as inpainting, super-resolution, image coloring, generative model inversion, etc.…
Reflective ptychography is a promising lensless imaging technique with a wide field of view, offering significant potential for applications in semiconductor manufacturing and detection. However, many semiconductor materials are coated with…
The design of functional materials with desired properties is essential in driving technological advances in areas like energy storage, catalysis, and carbon capture. Generative models provide a new paradigm for materials design by directly…
We propose Generative Probabilistic Image Colorization, a diffusion-based generative process that trains a sequence of probabilistic models to reverse each step of noise corruption. Given a line-drawing image as input, our method suggests…
Image inpainting techniques have shown promising improvement with the assistance of generative adversarial networks (GANs) recently. However, most of them often suffered from completed results with unreasonable structure or blurriness. To…