As most creatives working in the film and TV post production industry have been able to work remotely and largely as normal during lockdown, at least in theory, how have VFX houses coped with the pause in production that has surely affected their work pipelines and schedules? Following a period of readjustment while the technical […]
In the third new Informed Sauce podcast, HPE’s Chris Dando and Matt Dunning talk about the effect the lockdown has had on sourcing components and how the computer hardware industry has adapted in the unprecedented situation in which it finds itself. We also hear from HPE’s Graham Muncer ahead of the Discover Virtual Experience, which […]
The circular economy and technology renewal The potential benefits of ‘the circular economy’ on the global ecological health of our planet has been a major talking point amongst C-level executives for some time now. And it’s set to become a topic of concern throughout all levels of all organisations. After all, out of the office, […]
A big leap for image-based shape estimation Researchers at The University of Southern California, Facebook Reality Labs and Facebook AI Research have been working on the science of perfecting digital human sculpture using deep learning algorithms. Here is the abstract from the paper introducing PifuHD that they recently presented at CVPR 2020 “Recent advances in […]
Researchers at OpenAI have been able to train a machine learning model fed with pixel sequences to generate coherent images. This is another step toward understanding and bridging the gap between computer vision and language understanding techniques. Google’s BERT, Facebook’s RoBERTa, and OpenAI’s GPT-3 have made great strides with language tasks, but have hitherto been […]
This new NVIDIA project called StyleGAN2, presented at CVPR 2020, uses transfer learning to generate a seemingly infinite number of portraits in an infinite variety of painting styles. The work builds on the team’s previously published StyleGAN project. This new demo shows how the resulting machine learning training model can be used to create images and fluidly explore […]