Related papers: Image Shape Manipulation from a Single Augmented T…
Self-supervised learning has been known for learning good representations from data without the need for annotated labels. We explore the simple siamese (SimSiam) architecture for representation learning on strong gravitational lens images.…
Model-based single image dehazing algorithms restore images with sharp edges and rich details at the expense of low PSNR values. Data-driven ones restore images with high PSNR values but with low contrast, and even some remaining haze. In…
Generating high-resolution, photo-realistic images has been a long-standing goal in machine learning. Recently, Nguyen et al. (2016) showed one interesting way to synthesize novel images by performing gradient ascent in the latent space of…
In recent years, text-guided image manipulation has gained increasing attention in the multimedia and computer vision community. The input to conditional image generation has evolved from image-only to multimodality. In this paper, we study…
Diffusion models have the ability to generate high quality images by denoising pure Gaussian noise images. While previous research has primarily focused on improving the control of image generation through adjusting the denoising process,…
Visual generative AI models often encounter challenges related to text-image alignment and reasoning limitations. This paper presents a novel method for selectively enhancing the signal at critical denoising steps, optimizing image…
We study end-to-end learning strategies for 3D shape inference from images, in particular from a single image. Several approaches in this direction have been investigated that explore different shape representations and suitable learning…
Deep learning relies heavily on data augmentation to mitigate limited data, especially in medical imaging. Recent multimodal learning integrates text and images for segmentation, known as referring or text-guided image segmentation.…
Masked image modeling (MIM) with transformer backbones has recently been exploited as a powerful self-supervised pre-training technique. The existing MIM methods adopt the strategy to mask random patches of the image and reconstruct the…
Machine learning models are commonly trained end-to-end and in a supervised setting, using paired (input, output) data. Examples include recent super-resolution methods that train on pairs of (low-resolution, high-resolution) images.…
Photographers routinely compose multiple manipulated photos of the same scene (layers) into a single image, which is better than any individual photo could be alone. Similarly, 3D artists set up rendering systems to produce layered images…
Existing image-to-image transformation approaches primarily focus on synthesizing visually pleasing data. Generating images with correct identity labels is challenging yet much less explored. It is even more challenging to deal with image…
Single image generation (SIG), described as generating diverse samples that have similar visual content with the given single image, is first introduced by SinGAN which builds a pyramid of GANs to progressively learn the internal patch…
Multimode fiber~(MMF) imaging using deep learning has high potential to produce compact, minimally invasive endoscopic systems. Nevertheless, it relies on large, diverse real-world medical data, whose availability is limited by privacy…
Deep learning techniques have become widely utilized in histopathology image classification due to their superior performance. However, this success heavily relies on the availability of substantial labeled data, which necessitates…
Active soft bodies can affect their shape through an internal actuation mechanism that induces a deformation. Similar to recent work, this paper utilizes a differentiable, quasi-static, and physics-based simulation layer to optimize for…
We consider the targeted image editing problem: blending a region in a source image with a driver image that specifies the desired change. Differently from prior works, we solve this problem by learning a conditional probability…
Quantitative phase imaging (QPI) has been widely applied in characterizing cells and tissues. Spatial light interference microscopy (SLIM) is a highly sensitive QPI method, due to its partially coherent illumination and common path…
Generating a novel image by manipulating two input images is an interesting research problem in the study of generative adversarial networks (GANs). We propose a new GAN-based network that generates a fusion image with the identity of input…
Deep generative models, like GANs, have considerably improved the state of the art in image synthesis, and are able to generate near photo-realistic images in structured domains such as human faces. Based on this success, recent work on…