Related papers: ELIQ: A Label-Free Framework for Quality Assessmen…
Unsupervised image-to-image translation aims to learn the translation between two visual domains without paired data. Despite the recent progress in image translation models, it remains challenging to build mappings between complex domains…
Diffusion models have recently achieved remarkable photorealism, making it increasingly difficult to distinguish real images from generated ones, raising significant privacy and security concerns. In response, we present a key finding:…
The rapid advancement in generative AI models has enabled the creation of photorealistic images. At the same time, there are growing concerns about the potential misuse and dangers of generated content, as well as a pressing need for…
Generative AI, specifically text-to-image models, have revolutionized interior architectural design by enabling the rapid translation of conceptual ideas into visual representations from simple text prompts. While generative AI can produce…
Unpaired Image-to-Image Translation (UIT) focuses on translating images among different domains by using unpaired data, which has received increasing research focus due to its practical usage. However, existing UIT schemes defect in the…
Non-autoregressive generative transformers recently demonstrated impressive image generation performance, and orders of magnitude faster sampling than their autoregressive counterparts. However, optimal parallel sampling from the true joint…
Text-to-image models often struggle to generate images that precisely match textual prompts. Prior research has extensively studied the evaluation of image-text alignment in text-to-image generation. However, existing evaluations primarily…
In this paper, we design and train a Generative Image-to-text Transformer, GIT, to unify vision-language tasks such as image/video captioning and question answering. While generative models provide a consistent network architecture between…
Although noisy-label learning is often approached with discriminative methods for simplicity and speed, generative modeling offers a principled alternative by capturing the joint mechanism that produces features, clean labels, and corrupted…
Improving the aesthetic quality of images is challenging and eager for the public. To address this problem, most existing algorithms are based on supervised learning methods to learn an automatic photo enhancer for paired data, which…
Synthesis of digital artifacts conditioned on user prompts has become an important paradigm facilitating an explosion of use cases with generative AI. However, such models often fail to connect the generated outputs and desired target…
No-Reference Image Quality Assessment (NR-IQA) aims to develop methods to measure image quality in alignment with human perception without the need for a high-quality reference image. In this work, we propose a self-supervised approach…
Label-free model evaluation, or AutoEval, estimates model accuracy on unlabeled test sets, and is critical for understanding model behaviors in various unseen environments. In the absence of image labels, based on dataset representations,…
Autoregressive models have emerged as a powerful paradigm for visual content creation, but often overlook the intrinsic structural properties of visual data. Our prior work, IAR, initiated a direction to address this by reorganizing the…
Vision-Language Models (VLMs) are essential for embodied AI and safety-critical applications, such as robotics and autonomous systems. However, existing benchmarks primarily focus on static or curated visual inputs, neglecting the…
Recent advances in text-to-image (T2I) generation have achieved impressive results, yet existing models still struggle with prompts that require rich world knowledge and implicit reasoning: both of which are critical for producing…
In most real-world image-to-image (I2I) scenarios, existing evaluations primarily focus on instruction following and the perceptual quality or aesthetics of the generated images. However, they largely fail to assess whether the output image…
Warning: This paper contains several contents that may be toxic, harmful, or offensive. In the last few years, text-to-image generative models have gained remarkable success in generating images with unprecedented quality accompanied by a…
Learning a versatile language-image model is computationally prohibitive under a limited computing budget. This paper delves into the \emph{efficient language-image pre-training}, an area that has received relatively little attention…
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…