Author: Martin Anderson

A new  collaboration between researchers in Poland and the UK proposes the prospect of using Gaussian Splatting to edit images, by temporarily interpreting a selected part of the image into 3D space, allowing the user to modify and manipulate the 3D representation of the image, and then applying the transformation. To change the orientation of

New research from the US indicates that fine-tuning an AI foundation model on your own data does not need to reduce or impair the functionality of the original model – and that a relatively simple fix can not only restore the capabilities of the original model, but actually improve the quality of the output that

A new initiative from the Alibaba Group offers one of the best methods I have seen for generating full-body human avatars from a Stable Diffusion-based foundation model. Titled MIMO (MIMicking with Object Interactions), the system uses a range of popular technologies and modules, including CGI-based human models and AnimateDiff, to enable temporally consistent character replacement

New research from Singapore has proposed a novel method of detecting whether someone on the other end of a smartphone videoconferencing tool is using methods such as DeepFaceLive to impersonate someone else. Titled SFake , the new approach abandons the passive methods employed by most systems, and causes the user’s phone to vibrate (using the

The advent and progress of generative AI video has prompted many casual observers to predict that machine learning will prove the death of the movie industry as we know it – instead, single creators will be able to create Hollywood-style blockbusters at home, either on local or cloud-based GPU systems. Is this possible? Even if