相关论文: TIFA: Accurate and Interpretable Text-to-Image Fai…

Language models are increasingly being incorporated as components in larger AI systems for various purposes, from prompt optimization to automatic evaluation. In this work, we analyze the construct validity of four recent, commonly used…

Text-to-image generation and text-guided image manipulation have received considerable attention in the field of image generation tasks. However, the mainstream evaluation methods for these tasks have difficulty in evaluating whether all…

Recent text-to-image models have improved global realism, but text rendering remains a persistent failure mode: images may look convincing overall, yet local typography often contains malformed glyphs, broken strokes, irregular spacing, and…

Despite the impressive success of text-to-image (TTI) generation models, existing studies overlook the issue of whether these models accurately convey factual information. In this paper, we focus on the problem of image hallucination, where…

Despite their wide-spread success, Text-to-Image models (T2I) still struggle to produce images that are both aesthetically pleasing and faithful to the user's input text. We introduce DreamSync, a model-agnostic training algorithm by design…

Generating images from textual descriptions has recently attracted a lot of interest. While current models can generate photo-realistic images of individual objects such as birds and human faces, synthesising images with multiple objects is…

The rapid advancements of Text-to-Image (T2I) models have ushered in a new phase of AI-generated content, marked by their growing ability to interpret and follow user instructions. However, existing T2I model evaluation benchmarks fall…

The ideal form of Visual Question Answering requires understanding, grounding and reasoning in the joint space of vision and language and serves as a proxy for the AI task of scene understanding. However, most existing VQA benchmarks are…

In recent years, visual question answering (VQA) has become topical. The premise of VQA's significance as a benchmark in AI, is that both the image and textual question need to be well understood and mutually grounded in order to infer the…

With advances in the quality of text-to-image (T2I) models has come interest in benchmarking their prompt faithfulness -- the semantic coherence of generated images to the prompts they were conditioned on. A variety of T2I faithfulness…

Studies have shown that a dominant class of questions asked by visually impaired users on images of their surroundings involves reading text in the image. But today's VQA models can not read! Our paper takes a first step towards addressing…

Although recent text-to-image generative models have achieved impressive performance, they still often struggle with capturing the compositional complexities of prompts including attribute binding, and spatial relationships between…

Visual question answering is an important task in both natural language and vision understanding. However, in most of the public visual question answering datasets such as VQA, CLEVR, the questions are human generated that specific to the…

The field of text-conditioned image generation has made unparalleled progress with the recent advent of latent diffusion models. While remarkable, as the complexity of given text input increases, the state-of-the-art diffusion models may…

Text-to-image diffusion models have achieved remarkable success, yet generating coherent image sequences for visual storytelling remains challenging. A key challenge is effectively leveraging all previous text-image pairs, referred to as…

Text-to-Image generation has evolved from basic image synthesis into a frequently used core capability in professional creative workflows, where simple text-image alignment can no longer satisfy users' pressing demands for faithful…

We propose the inverse problem of Visual question answering (iVQA), and explore its suitability as a benchmark for visuo-linguistic understanding. The iVQA task is to generate a question that corresponds to a given image and answer pair.…

We present VISTAR, a user-centric, multi-dimensional benchmark for text-to-image (T2I) evaluation that addresses the limitations of existing metrics. VISTAR introduces a two-tier hybrid paradigm: it employs deterministic, scriptable metrics…

While text-to-image (T2I) generative models have become ubiquitous, they do not necessarily generate images that align with a given prompt. While previous work has evaluated T2I alignment by proposing metrics, benchmarks, and templates for…

Evaluating the quality of synthesized images remains a significant challenge in the development of text-to-image (T2I) generation. Most existing studies in this area primarily focus on evaluating text-image alignment, image quality, and…