相关论文: Approximating Human Judgment of Generated Image Qu…

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…

The aesthetic quality of an image is defined as the measure or appreciation of the beauty of an image. Aesthetics is inherently a subjective property but there are certain factors that influence it such as, the semantic content of the…

Image classifiers should be used with caution in the real world. Performance evaluated on a validation set may not reflect performance in the real world. In particular, classifiers may perform well for conditions that are frequently…

The increasing realism of generated images has raised significant concerns about their potential misuse, necessitating robust detection methods. Current approaches mainly rely on training binary classifiers, which depend heavily on the…

Recent advancements in text-to-image (T2I) generation models have transformed the field. However, challenges persist in generating images that reflect demanding textual descriptions, especially for fine-grained details and unusual…

How humans interpret and produce images is influenced by the images we have been exposed to. Similarly, visual generative AI models are exposed to many training images and learn to generate new images based on this. Given the importance of…

Photo collections and its applications today attempt to reflect user interactions in various forms. Moreover, photo collections aim to capture the users' intention with minimum effort through applications capturing user intentions. Human…

In today's age of internet and social media, one can find an enormous volume of forged images on-line. These images have been used in the past to convey falsified information and achieve harmful intentions. The spread and the effect of the…

Score-based generative models can produce high quality image samples comparable to GANs, without requiring adversarial optimization. However, existing training procedures are limited to images of low resolution (typically below 32x32), and…

In the e-commerce realm, compelling advertising images are pivotal for attracting customer attention. While generative models automate image generation, they often produce substandard images that may mislead customers and require…

Benchmark datasets in computer vision often contain off-topic images, near duplicates, and label errors, leading to inaccurate estimates of model performance. In this paper, we revisit the task of data cleaning and formalize it as either a…

Evaluating generative models remains a fundamental challenge, particularly when the goal is to reflect human preferences. In this paper, we use music generation as a case study to investigate the gap between automatic evaluation metrics and…

Face image quality can be defined as a measure of the utility of a face image to automatic face recognition. In this work, we propose (and compare) two methods for automatic face image quality based on target face quality values from (i)…

We propose a training and evaluation approach for autoencoder Generative Adversarial Networks (GANs), specifically the Boundary Equilibrium Generative Adversarial Network (BEGAN), based on methods from the image quality assessment…

With the rapid advancement of generative models, highly realistic image synthesis has posed new challenges to digital security and media credibility. Although AI-generated image detection methods have partially addressed these concerns, a…

Research on generative models to produce human-aligned / human-preferred outputs has seen significant recent contributions. Between text and image-generative models, we narrowed our focus to text-based generative models, particularly to…

Despite rapid advances in video generative models, robust metrics for evaluating visual and temporal correctness of complex human actions remain elusive. Critically, existing pure-vision encoders and Multimodal Large Language Models (MLLMs)…

Decades of psychological research have been aimed at modeling how people learn features and categories. The empirical validation of these theories is often based on artificial stimuli with simple representations. Recently, deep neural…

Hand-crafted image quality metrics, such as PSNR and SSIM, are commonly used to evaluate model privacy risk under reconstruction attacks. Under these metrics, reconstructed images that are determined to resemble the original one generally…

We present a full reference, perceptual image metric based on VGG-16, an artificial neural network trained on object classification. We fit the metric to a new database based on 140k unique images annotated with ground truth by human raters…