Related papers: Contrastive Feature Loss for Image Prediction
Image completion has achieved significant progress due to advances in generative adversarial networks (GANs). Albeit natural-looking, the synthesized contents still lack details, especially for scenes with complex structures or images with…
The goal of text-to-image synthesis is to generate a visually realistic image that matches a given text description. In practice, the captions annotated by humans for the same image have large variance in terms of contents and the choice of…
Ensuring the realism of computer-generated synthetic images is crucial to deep neural network (DNN) training. Due to different semantic distributions between synthetic and real-world captured datasets, there exists semantic mismatch between…
The recent demand for customized image generation raises a need for techniques that effectively extract the common concept from small sets of images. Existing methods typically rely on additional guidance, such as text prompts or spatial…
In image editing, the most common task is pasting objects from one image to the other and then eventually adjusting the manifestation of the foreground object with the background object. This task is called image compositing. But image…
One of the major challenges in training deep neural networks for text-to-image generation is the significant linguistic discrepancy between ground-truth captions of each image in most popular datasets. The large difference in the choice of…
In image-to-image translation, each patch in the output should reflect the content of the corresponding patch in the input, independent of domain. We propose a straightforward method for doing so -- maximizing mutual information between the…
New advancements for the detection of synthetic images are critical for fighting disinformation, as the capabilities of generative AI models continuously evolve and can lead to hyper-realistic synthetic imagery at unprecedented scale and…
Fine-grained text to image synthesis involves generating images from texts that belong to different categories. In contrast to general text to image synthesis, in fine-grained synthesis there is high similarity between images of different…
Self-supervised learning enables networks to learn discriminative features from massive data itself. Most state-of-the-art methods maximize the similarity between two augmentations of one image based on contrastive learning. By utilizing…
Unpaired image-to-image translation aims to find a mapping between the source domain and the target domain. To alleviate the problem of the lack of supervised labels for the source images, cycle-consistency based methods have been proposed…
Counterfactuals are a popular framework for interpreting machine learning predictions. These what if explanations are notoriously challenging to create for computer vision models: standard gradient-based methods are prone to produce…
As synthetic imagery is used more frequently in training deep models, it is important to understand how different synthesis techniques impact the performance of such models. In this work, we perform a thorough evaluation of the…
Recent approaches in generative adversarial networks (GANs) can automatically synthesize realistic images from descriptive text. Despite the overall fair quality, the generated images often expose visible flaws that lack structural…
Feed-forward CNNs trained for image transformation problems rely on loss functions that measure the similarity between the generated image and a target image. Most of the common loss functions assume that these images are spatially aligned…
In this paper we show how to learn directly from image data (i.e., without resorting to manually-designed features) a general similarity function for comparing image patches, which is a task of fundamental importance for many computer…
In the last few years, the artifact patterns in fake images synthesized by different generative models have been inconsistent, leading to the failure of previous research that relied on spotting subtle differences between real and fake. In…
Maintaining natural image statistics is a crucial factor in restoration and generation of realistic looking images. When training CNNs, photorealism is usually attempted by adversarial training (GAN), that pushes the output images to lie on…
The heightened realism of AI-generated images can be attributed to the rapid development of synthetic models, including generative adversarial networks (GANs) and diffusion models (DMs). The malevolent use of synthetic images, such as the…
Supervised and unsupervised homography estimation methods depend on image pairs tailored to specific modalities to achieve high accuracy. However, their performance deteriorates substantially when applied to unseen modalities. To address…