Related papers: Composition and Deformance: Measuring Imageability…
Text to Image Synthesis refers to the process of automatic generation of a photo-realistic image starting from a given text and is revolutionizing many real-world applications. In order to perform such process it is necessary to exploit…
Many machine learning algorithms represent input data with vector embeddings or discrete codes. When inputs exhibit compositional structure (e.g. objects built from parts or procedures from subroutines), it is natural to ask whether this…
Personalized text-to-image models allow users to generate varied styles of images (specified with a sentence) for an object (specified with a set of reference images). While remarkable results have been achieved using diffusion-based…
The progress in the generation of synthetic images has made it crucial to assess their quality. While several metrics have been proposed to assess the rendering of images, it is crucial for Text-to-Image (T2I) models, which generate images…
Text-to-image diffusion models have demonstrated remarkable capability in generating realistic images from arbitrary text prompts. However, they often produce inconsistent results for compositional prompts such as "two dogs" or "a penguin…
This paper proposes a simple test for compositionality (i.e., literal usage) of a word or phrase in a context-specific way. The test is computationally simple, relying on no external resources and only uses a set of trained word vectors.…
The goal of this paper is to embed controllable factors, i.e., natural language descriptions, into image-to-image translation with generative adversarial networks, which allows text descriptions to determine the visual attributes of…
One of the latest applications of Artificial Intelligence (AI) is to generate images from natural language descriptions. These generators are now becoming available and achieve impressive results that have been used for example in the front…
Most text-to-image customization techniques fine-tune models on a small set of \emph{personal concept} images captured in minimal contexts. This often results in the model becoming overfitted to these training images and unable to…
Text-to-image generative models have achieved remarkable visual quality but still struggle with compositionality$-$accurately capturing object relationships, attribute bindings, and fine-grained details in prompts. A key limitation is that…
Customized text-to-image generation, which aims to learn user-specified concepts with a few images, has drawn significant attention recently. However, existing methods usually suffer from overfitting issues and entangle the…
Compositional reasoning is a hallmark of human visual intelligence. Yet, despite the size of large vision-language models, they struggle to represent simple compositions by combining objects with their attributes. To measure this lack of…
Personalized text-to-image generation has attracted unprecedented attention in the recent few years due to its unique capability of generating highly-personalized images via using the input concept dataset and novel textual prompt. However,…
We provide a new multi-task benchmark for evaluating text-to-image models. We perform a human evaluation comparing the most common open-source (Stable Diffusion) and commercial (DALL-E 2) models. Twenty computer science AI graduate students…
Vision-Language Models (VLMs) learn a shared feature space for text and images, enabling the comparison of inputs of different modalities. While prior works demonstrated that VLMs organize natural language representations into regular…
Idiomatic expressions are an integral part of human languages, often used to express complex ideas in compressed or conventional ways (e.g. eager beaver as a keen and enthusiastic person). However, their interpretations may not be…
Training audio-to-image generative models requires an abundance of diverse audio-visual pairs that are semantically aligned. Such data is almost always curated from in-the-wild videos, given the cross-modal semantic correspondence that is…
Taking advantage of the many recent advances in deep learning, text-to-image generative models currently have the merit of attracting the general public attention. Two of these models, DALL-E 2 and Imagen, have demonstrated that highly…
Subject-driven text-to-image generation still struggles to preserve high-frequency identity details such as logos, patterns, and text. Existing methods typically operate directly in RGB space, which often leads to detail degradation under…
Text-to-image generation methods produce high-resolution and high-quality images, but these methods should not produce immoral images that may contain inappropriate content from the perspective of commonsense morality. In this paper, we aim…