Related papers: Degradation-Modeled Multipath Diffusion for Tunabl…
Modern nanofabrication techniques have enabled us to manipulate the wavefront of light with sub-wavelength-scale structures, offering the potential to replace bulky refractive surfaces in conventional optics with ultrathin metasurfaces. In…
Recent advances in text-to-image generation with diffusion models present transformative capabilities in image quality. However, user controllability of the generated image, and fast adaptation to new tasks still remains an open challenge,…
Image matting aims to predict alpha values of elaborate uncertainty areas of natural images, like hairs, smoke, and spider web. However, existing methods perform poorly when faced with highly transparent foreground objects due to the large…
Metasurface optics provide an ultra-thin alternative to conventional refractive lenses. A present challenge is in realizing metasurfaces that exhibit tunable optical properties and achromatic behavior across the visible spectrum. Here, we…
Real-world image restoration is hampered by diverse degradations stemming from varying capture conditions, capture devices and post-processing pipelines. Existing works make improvements through simulating those degradations and leveraging…
Diffusion models, known for their powerful generative capabilities, play a crucial role in addressing real-world super-resolution challenges. However, these models often focus on improving local textures while neglecting the impacts of…
Radiation hazards associated with standard-dose positron emission tomography (SPET) images remain a concern, whereas the quality of low-dose PET (LPET) images fails to meet clinical requirements. Therefore, there is great interest in…
Recently, metalenses which consist of metasurface arrays, have attracted attention due to their more condensed size in comparison with conventional lenses. In this paper, we propose a reconfigurable coding metasurface hybridized with…
Diffusion models have recently gained traction as a powerful class of deep generative priors, excelling in a wide range of image restoration tasks due to their exceptional ability to model data distributions. To solve image restoration…
Denoising diffusion models have emerged as the go-to generative framework for solving inverse problems in imaging. A critical concern regarding these models is their performance on out-of-distribution tasks, which remains an under-explored…
In medical imaging, the diffusion models have shown great potential for synthetic image generation tasks. However, these approaches often lack the interpretable connections between the generated and real images and can create anatomically…
Diffusion models have demonstrated their powerful image generation capabilities, effectively fitting highly complex image distributions. These models can serve as strong priors for image restoration. Existing methods often utilize…
Color plays an important role in human visual perception, reflecting the spectrum of objects. However, the existing infrared and visible image fusion methods rarely explore how to handle multi-spectral/channel data directly and achieve high…
Nonlinear light sources are central to a myriad of applications, driving a quest for their miniaturisation down to the nanoscale. In this quest, nonlinear metasurfaces hold a great promise, as they enhance nonlinear effects through their…
The conventional lens's tunability drawback always restricts their application compared to the metasurface lens (metalens). On the other side, reconfigurable metalenses offer the benefits of ultrathin thickness and capable of tunability.…
Diffusion models (DMs) have exhibited remarkable efficacy in various image restoration tasks. However, existing approaches typically operate within the high-dimensional pixel space, resulting in high computational overhead. While methods…
Current text-to-image diffusion models excel at generating diverse, high-quality images, yet they struggle to incorporate fine-grained camera metadata such as precise aperture settings. In this work, we introduce a novel text-to-image…
Multi-foci metalenses with uniform focal arrays attract special attention as they enable a single incident beam to focus on the same focal plane and share the identical numerical apertures. In this work, we demonstrate the scalable…
Metasurface lenses, namely metalenses, are ultrathin planar nanostructures that are capable of manipulating the properties of incoming light and imparting lens-like wavefront to the output. Although they have shown promising potentials for…
By decomposing the image formation process into a sequential application of denoising autoencoders, diffusion models (DMs) achieve state-of-the-art synthesis results on image data and beyond. Additionally, their formulation allows for a…