Related papers: PGC: Peak-Guided Calibration for Generalizable AI-…
The aim of this work is to explore the potential of pre-trained vision-language models (VLMs) for universal detection of AI-generated images. We develop a lightweight detection strategy based on CLIP features and study its performance in a…
It is common but challenging to address high-resolution image blending in the automatic photo editing application. In this paper, we would like to focus on solving the problem of high-resolution image blending, where the composite images…
Existing generative adversarial network (GAN) based conditional image generative models typically produce fixed output for the same conditional input, which is unreasonable for highly subjective tasks, such as large-mask image inpainting or…
Detecting AI-generated images, particularly deepfakes, has become increasingly crucial, with the primary challenge being the generalization to previously unseen manipulation methods. This paper tackles this issue by leveraging the forgery…
Image Quality Assessment (IQA) models are employed in many practical image and video processing pipelines to reduce storage, minimize transmission costs, and improve the Quality of Experience (QoE) of millions of viewers. These models are…
With growing abilities of generative models, artificial content detection becomes an increasingly important and difficult task. However, all popular approaches to this problem suffer from poor generalization across domains and generative…
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…
Convolution-based and Transformer-based vision backbone networks process images into the grid or sequence structures, respectively, which are inflexible for capturing irregular objects. Though Vision GNN (ViG) adopts graph-level features…
Gaussian processes are notorious for scaling cubically with the size of the training set, preventing application to very large regression problems. Computation-aware Gaussian processes (CAGPs) tackle this scaling issue by exploiting…
3D Gaussian Splatting (3DGS) enables photorealistic rendering but suffers from artefacts due to sparse Structure-from-Motion (SfM) initialisation. To address this limitation, we propose GP-GS, a Gaussian Process (GP) based densification…
In recent years, numerous graph generative models (GGMs) have been proposed. However, evaluating these models remains a considerable challenge, primarily due to the difficulty in extracting meaningful graph features that accurately…
The rapid advancement of generative artificial intelligence has enabled the creation of synthetic images that are increasingly indistinguishable from authentic content, posing significant challenges for digital media integrity. This problem…
Recent advances in generative models have highlighted the need for robust detectors capable of distinguishing real images from AI-generated images. While existing methods perform well on known generators, their performance often declines…
In prediction problems, it is common to model the data-generating process and then use a model-based procedure, such as a Bayesian predictive distribution, to quantify uncertainty about the next observation. However, if the posited model is…
Recently, AI-generated images (AIGIs) created by given prompts (initial prompts) have garnered widespread attention. Nevertheless, due to technical nonproficiency, they often suffer from poor perception quality and Text-to-Image…
Recent advancements in generative models have significantly facilitated the development of personalized content creation. Given a small set of images with user-specific concept, personalized image generation allows to create images that…
One of the key challenges of detecting AI-generated images is spotting images that have been created by previously unseen generative models. We argue that the limited diversity of the training data is a major obstacle to addressing this…
Detecting small objects is notoriously challenging due to their low resolution and noisy representation. Existing object detection pipelines usually detect small objects through learning representations of all the objects at multiple…
Successful forensic detectors can produce excellent results in supervised learning benchmarks but struggle to transfer to real-world applications. We believe this limitation is largely due to inadequate training data quality. While most…
Class imbalance occurs in many real-world applications, including image classification, where the number of images in each class differs significantly. With imbalanced data, the generative adversarial networks (GANs) leans to majority class…