State-of-the-Art

LCM-LoRA: Real-Time Image Generation Neural Network

Researchers at Tsinghua University have developed the LCM-LoRA algorithm, revolutionizing real-time image generation from text descriptions or sketches. Consequently, this technology marks a significant advancement in the field. Popular text-to-image…
News

NVIDIA Eureka: Agent for Autonomous Robot Learning

NVIDIA has unveiled Eureka, an open-source agent based on GPT-4, designed to teach robots complex skills such as performing tricks and handling scissors. This breakthrough leverages the power of large…
News

Google Introduces Image Generation in Search

Google has announced the integration of image generation in search results based on descriptions and several other AI features. Furthermore, this tool is built on the Imagen model and allows…
State-of-the-Art

TransGAN: two Transformer models as one GAN

TransGAN is a GAN model in which the generator and discriminator are composed of two Transformer architectures. GAN architecture traditionally uses convolutions. In TransGAN, convolutions are replaced with Transformer. The…
Architectures

U-Net: Image Segmentation Network

U-Net is considered one of the standard CNN architectures for image classification tasks, when we need not only to define the whole image by its class but also to segment areas of…
Datasets

New Datasets for 3D Human Pose Estimation

Human pose estimation is а fundamental problem in computer vision. Computer’s ability to recognize and understand humans in images and videos is crucial for multiple tasks including autonomous driving, action…