Related papers: LEGION: Learning to Ground and Explain for Synthet…

As the misuse of AI-generated images grows, generalizable image detection techniques are urgently needed. Recent state-of-the-art (SOTA) methods adopt aligned training datasets to reduce content, size, and format biases, empowering models…

This article aims to use graphic engines to simulate a large number of training data that have free annotations and possibly strongly resemble to real-world data. Between synthetic and real, a two-level domain gap exists, involving content…

In this paper we introduce a new method for text detection in natural images. The method comprises two contributions: First, a fast and scalable engine to generate synthetic images of text in clutter. This engine overlays synthetic text to…

Line segments are ubiquitous in our human-made world and are increasingly used in vision tasks. They are complementary to feature points thanks to their spatial extent and the structural information they provide. Traditional line detectors…

With the rapid advancement of generative AI, it is now possible to synthesize high-quality images in a few seconds. Despite the power of these technologies, they raise significant concerns regarding misuse. Current efforts to distinguish…

Camouflaged objects that blend into natural scenes pose significant challenges for deep-learning models to detect and synthesize. While camouflaged object detection is a crucial task in computer vision with diverse real-world applications,…

The growing prevalence of tampered images poses serious security threats, highlighting the urgent need for reliable detection methods. Multimodal large language models (MLLMs) demonstrate strong potential in analyzing tampered images and…

As latent diffusion models (LDMs) democratize image generation capabilities, there is a growing need to detect fake images. A good detector should focus on the generative models fingerprints while ignoring image properties such as semantic…

While synthetic data has proven effective for improving scientific reasoning in the text domain, multimodal reasoning remains constrained by the difficulty of synthesizing scientifically rigorous images. Existing Text-to-Image (T2I) models…

Linguistic steganography provides convenient implementation to hide messages, particularly with the emergence of AI generation technology. The potential abuse of this technology raises security concerns within societies, calling for…

The generative AI technology offers an increasing variety of tools for generating entirely synthetic images that are increasingly indistinguishable from real ones. Unlike methods that alter portions of an image, the creation of completely…

Typical methods for text-to-image synthesis seek to design effective generative architecture to model the text-to-image mapping directly. It is fairly arduous due to the cross-modality translation. In this paper we circumvent this problem…

Fine-tuning for large language models (LLMs) typically requires substantial amounts of high-quality supervised data, which is both costly and labor-intensive to acquire. While synthetic data generation has emerged as a promising solution,…

Deep learning models have demonstrated remarkable performance across various computer vision tasks, yet their vulnerability to distribution shifts remains a critical challenge. Despite sophisticated neural network architectures, existing…

We introduce AEGIS, A holistic benchmark for Evaluating forensic analysis of AI-Generated academic ImageS. Compared to existing benchmarks, AEGIS features three key advances: (1) Domain-Specific Complexity: covering seven academic…

The digitization of documents allows for wider accessibility and reproducibility. While automatic digitization of document layout and text content has been a long-standing focus of research, this problem in regard to graphical elements,…

The rapid progress of generative models has enabled the creation of highly realistic synthetic images, raising concerns about authenticity and trust in digital media. Detecting such fake content reliably is an urgent challenge. While deep…

A key algorithm for understanding the world is material segmentation, which assigns a label (metal, glass, etc.) to each pixel. We find that a model trained on existing data underperforms in some settings and propose to address this with a…

A promise of Generative Adversarial Networks (GANs) is to provide cheap photorealistic data for training and validating AI models in autonomous driving. Despite their huge success, their performance on complex images featuring multiple…

At this moment, GAN-based image generation methods are still imperfect, whose upsampling design has limitations in leaving some certain artifact patterns in the synthesized image. Such artifact patterns can be easily exploited (by recent…