Related papers: Diffusion Models as Artists: Are we Closing the Ga…
In this work, we investigate an intriguing and prevalent phenomenon of diffusion models which we term as "consistent model reproducibility": given the same starting noise input and a deterministic sampler, different diffusion models often…
The rapid progress in generative models has given rise to the critical task of AI-Generated Content Stealth (AIGC-S), which aims to create AI-generated images that can evade both forensic detectors and human inspection. This task is crucial…
Human body restoration plays a vital role in various applications related to the human body. Despite recent advances in general image restoration using generative models, their performance in human body restoration remains mediocre, often…
Image generation techniques, particularly latent diffusion models, have exploded in popularity in recent years. Many techniques have been developed to manipulate and clarify the semantic concepts these large-scale models learn, offering…
Accurate evaluation of human aesthetic preferences represents a major challenge for creative evolutionary and generative systems research. Prior work has tended to focus on feature measures of the artefact, such as symmetry, complexity and…
The image deepfake detection task has been greatly addressed by the scientific community to discriminate real images from those generated by Artificial Intelligence (AI) models: a binary classification task. In this work, the deepfake…
Diffusion models are now the undisputed state-of-the-art for image generation and image restoration. However, they require large amounts of computational power for training and inference. In this paper, we propose lightweight diffusion…
Visual saliency models have enjoyed a big leap in performance in recent years, thanks to advances in deep learning and large scale annotated data. Despite enormous effort and huge breakthroughs, however, models still fall short in reaching…
By comparing biological and artificial perception through the lens of illusions, we highlight critical differences in how each system constructs visual reality. Understanding these divergences can inform the development of more robust,…
Humans represent scenes and objects in rich feature spaces, carrying information that allows us to generalise about category memberships and abstract functions with few examples. What determines whether a neural network model generalises…
Deep ensembles excel in large-scale image classification tasks both in terms of prediction accuracy and calibration. Despite being simple to train, the computation and memory cost of deep ensembles limits their practicability. While some…
Generative Artificial Intelligence (AI) has advanced rapidly, enabling the generation of renderings from architectural sketches. This progress has significantly improved the efficiency of communication and conceptual expression during the…
Diffusion models, trained on large amounts of data, showed remarkable performance for image synthesis. They have high error consistency with humans and low texture bias when used for classification. Furthermore, prior work demonstrated the…
A central goal in AI is to represent scenes as compositions of discrete objects, enabling fine-grained, controllable image and video generation. Yet leading diffusion models treat images holistically and rely on text conditioning, creating…
Visually identifying materials is crucial for many tasks, yet material perception remains poorly understood. Distinguishing mirror from glass is particularly challenging as both materials derive their appearance from their surroundings, yet…
An important goal in human-robot-interaction (HRI) is for machines to achieve a close to human level of face perception. One of the important differences between machine learning and human intelligence is the lack of compositionality. This…
The integration of artificial intelligence (AI), particularly Convolutional Neural Networks (CNNs), into dermatological diagnosis demonstrates substantial clinical potential. While existing literature predominantly benchmarks algorithmic…
Face recognition and verification are two computer vision tasks whose performance has progressed with the introduction of deep representations. However, ethical, legal, and technical challenges due to the sensitive character of face data…
We introduce a novel framework for human-AI collaboration in prediction and decision tasks. Our approach leverages human judgment to distinguish inputs which are algorithmically indistinguishable, or "look the same" to any feasible…
AI systems increasingly support human decision-making. In many cases, despite the algorithm's superior performance, the final decision remains in human hands. For example, an AI may assist doctors in determining which diagnostic tests to…