Attempting to make precise compositions with latent diffusion generative image models such as Stable Diffusion can be like herding cats; the very same imaginative and interpretive...
Google Research, it seems, is attacking text-based image-editing from a number of fronts, and, presumably, waiting to see what ‘takes’. Hot on the trail of this...
Anyone who has learned Italian learns early to pay attention to context when describing a broom, because the Italian word for this mundane domestic item has...
This week two new, but contrasting AI-driven graphics algorithms are offering novel ways for end users to make highly granular and effective changes to objects in...
New research from New York University adds to the growing indications that we may soon have to take the deepfake equivalent of a ‘drunk test’ in...
Opinion Of late, the deepfake detection research community, which has since late 2017 been occupied almost exclusively with the autoencoder-based framework that premiered at that time...
The image synthesis research sector is thickly littered with new proposals for systems capable of creating full-body video and pictures of young people – mainly young...
A new paper from the Hyundai Motor Group Innovation Center at Singapore offers a method for separating ‘fused’ humans in computer vision – those cases where...
New research from the University of Michigan proffers a way for robots to understand the mechanisms of tools, and other real-world articulated objects, by creating Neural...
The most well-known line of inquiry in the growing anti-deepfake research sector involves systems that can recognize artifacts or other supposedly distinguishing characteristics of deepfaked, synthesized,...
Ironically, Stable Diffusion, the new AI image synthesis framework that has taken the world by storm, is neither stable nor really that ‘diffused’ – at least,...
The release of stability.ai’s Stable Diffusion latent diffusion image synthesis model a couple of weeks ago may be one of the most significant technological disclosures since...
Findings from a new paper indicate that state-of-the-art AI is significantly less able to recognize and interpret AI-synthesized images than people, which may be of concern...
New research from Italy has found that depth information obtained from images can be a useful tool to detect deepfakes – even in real-time. Whereas the...
A new study from the UK has concluded that lossy compression techniques in JPEG images can have an adverse influence on the effectiveness of facial recognition...
