As has been mentioned here previously, if restless creative minds are allowed too much time and unfettered access to digital technology, especially machine learning tools, things can get weird quite quickly. Wag Denis Malimonov, whose aim is to popularise the creation of art using machine learning, fed the PULSE (Photo Upsampling Via Latent Space Exploration) […]
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 […]
A team of researchers at Duke University in the US led by computer scientists Cynthia Rudin has successfully used machine learning to convert blurry portrait photos containing just a few dozen pixels into a super high-resolution images. The PULSE (Photo Upsampling via Latent Space Exploration) system works by reverse engineering the image from AI-generated high […]
Five university researchers from Hong Kong and China have created an application called DeepFaceDrawing which “allows users with little training in drawing to produce high-quality images from rough or even incomplete freehand sketches”. Abstract of the team’s academic paper Recent deep image-to-image translation techniques allow fast generation of face images from freehand sketches. However, existing solutions tend […]