Related papers: LDM-ISP: Enhancing Neural ISP for Low Light with L…
Enhancing the quality of low-light images plays a very important role in many image processing and multimedia applications. In recent years, a variety of deep learning techniques have been developed to address this challenging task. A…
Complex degradations like noise, blur, and low resolution are typical challenges in real world image fusion tasks, limiting the performance and practicality of existing methods. End to end neural network based approaches are generally…
Denosing diffusion model, as a generative model, has received a lot of attention in the field of image generation recently, thanks to its powerful generation capability. However, diffusion models have not yet received sufficient research in…
DNN-based methods have been successful in Image Signal Processor (ISP) and image enhancement (IE) tasks. However, the cost of creating training data for these tasks is considerably higher than for other tasks, making it difficult to prepare…
In recent years, the introduction of deep learning into the field of single-pixel imaging has garnered significant attention. However, traditional networks often operate within the pixel space. To address this, we innovatively migrate…
Capturing images is a key part of automation for high-level tasks such as scene text recognition. Low-light conditions pose a challenge for high-level perception stacks, which are often optimized on well-lit, artifact-free images.…
Generative techniques for image anonymization have great potential to generate datasets that protect the privacy of those depicted in the images, while achieving high data fidelity and utility. Existing methods have focused extensively on…
Diffusion models achieve state-of-the-art generative performance but suffer from high computational costs during inference due to the repeated evaluation of a heavy neural network. In this work, we propose Dual-Rate Diffusion, a method to…
Image-to-Image translation models can help mitigate various challenges inherent to medical image acquisition. Latent diffusion models (LDMs) leverage efficient learning in compressed latent space and constitute the core of state-of-the-art…
Instead of performing text-conditioned denoising in the image domain, latent diffusion models (LDMs) operate in latent space of a variational autoencoder (VAE), enabling more efficient processing at reduced computational costs. However,…
The tremendous progress in neural image generation, coupled with the emergence of seemingly omnipotent vision-language models has finally enabled text-based interfaces for creating and editing images. Handling generic images requires a…
Diffusion models have emerged as powerful tools for solving inverse problems due to their exceptional ability to model complex prior distributions. However, existing methods predominantly assume known forward operators (i.e., non-blind),…
Contrast enhancement and noise removal are coupled problems for low-light image enhancement. The existing Retinex based methods do not take the coupling relation into consideration, resulting in under or over-smoothing of the enhanced…
Three-dimensional imaging plays an important role in imaging applications where it is necessary to record depth. The number of applications that use depth imaging is increasing rapidly, and examples include self-driving autonomous vehicles…
Full DNN-based image signal processors (ISPs) have been actively studied and have achieved superior image quality compared to conventional ISPs. In contrast to this trend, we propose a lightweight ISP that consists of simple conventional…
Multiple low-vision tasks such as denoising, deblurring and super-resolution depart from RGB images and further reduce the degradations, improving the quality. However, modeling the degradations in the sRGB domain is complicated because of…
We introduce a deep learning approach to realistically edit an sRGB image's white balance. Cameras capture sensor images that are rendered by their integrated signal processor (ISP) to a standard RGB (sRGB) color space encoding. The ISP…
It is suggested that low-light image enhancement realizes one-to-many mapping since we have different definitions of NORMAL-light given application scenarios or users' aesthetic. However, most existing methods ignore subjectivity of the…
Latent diffusion models offer an attractive alternative to discrete diffusion for non-autoregressive text generation by operating on continuous text representations and denoising entire sequences in parallel. The major challenge in latent…
The recent use of diffusion prior, enhanced by pre-trained text-image models, has markedly elevated the performance of image super-resolution (SR). To alleviate the huge computational cost required by pixel-based diffusion SR, latent-based…