Related papers: WILD: a new in-the-Wild Image Linkage Dataset for …

AI-generated images have become increasingly realistic and have garnered significant public attention. While synthetic images are intriguing due to their realism, they also pose an important misinformation threat. To address this new…

Distribution shifts -- where the training distribution differs from the test distribution -- can substantially degrade the accuracy of machine learning (ML) systems deployed in the wild. Despite their ubiquity in the real-world deployments,…

Synthetic image source attribution is a challenging task, especially in data scarcity conditions requiring few-shot or zero-shot classification capabilities. We present a new training-free one-shot attribution method based on image…

While large text-to-image models are able to synthesize "novel" images, these images are necessarily a reflection of the training data. The problem of data attribution in such models -- which of the images in the training set are most…

Most publicly available image quality databases have been created under highly controlled conditions by introducing graded simulated distortions onto high-quality photographs. However, images captured using typical real-world mobile camera…

Collections of images under a single, uncontrolled illumination have enabled the rapid advancement of core computer vision tasks like classification, detection, and segmentation. But even with modern learning techniques, many inverse…

The rapid advancement of generative Artificial Intelligence (AI) has introduced significant challenges for reliable AI-generated image detection. Existing detectors often suffer from performance degradation under distribution shifts and…

This paper presents an overview of the NTIRE 2026 Challenge on Robust AI-Generated Image Detection in the Wild, held in conjunction with the NTIRE workshop at CVPR 2026. The goal of this challenge was to develop detection models capable of…

Machine learning systems deployed in the wild are often trained on a source distribution but deployed on a different target distribution. Unlabeled data can be a powerful point of leverage for mitigating these distribution shifts, as it is…

The steady improvement of Diffusion Models for visual synthesis has given rise to many new and interesting use cases of synthetic images but also has raised concerns about their potential abuse, which poses significant societal threats. To…

The rapid advancement of generative AI has enabled the creation of highly realistic and diverse synthetic images, posing critical challenges for image provenance and misinformation detection. This underscores the urgent need for effective…

Synthetic image data generation represents a promising avenue for training deep learning models, particularly in the realm of transfer learning, where obtaining real images within a specific domain can be prohibitively expensive due to…

We present WinSyn, a unique dataset and testbed for creating high-quality synthetic data with procedural modeling techniques. The dataset contains high-resolution photographs of windows, selected from locations around the world, with 89,318…

Open-source Vision-Language Models show immense promise for enterprise applications, yet a critical disconnect exists between academic evaluation and enterprise deployment requirements. Current benchmarks rely heavily on multiple-choice…

Rapid advances in generative AI have enabled the creation of highly realistic synthetic images, which, while beneficial in many domains, also pose serious risks in terms of disinformation, fraud, and other malicious applications. Current…

The large abundance of perspective camera datasets facilitated the emergence of novel learning-based strategies for various tasks, such as camera localization, single image depth estimation, or view synthesis. However, panoramic or…

Visual designers naturally draw inspiration from multiple visual references, combining diverse elements and aesthetic principles to create artwork. However, current image generative frameworks predominantly rely on single-source inputs --…

We introduce a data-driven approach for interactively synthesizing in-the-wild images from semantic label maps. Our approach is dramatically different from recent work in this space, in that we make use of no learning. Instead, our approach…

Significant progress has been made in detecting synthetic images, however most existing approaches operate on a single image instance and overlook a key characteristic of real-world dissemination: as viral images circulate on the web,…

The goal of data attribution for text-to-image models is to identify the training images that most influence the generation of a new image. Influence is defined such that, for a given output, if a model is retrained from scratch without the…